Skip to main content

Sreeram Kannan

  • Assistant Professor

Kannan runs the Information theory lab with research interests in information theory, which deals with the fundamentals of information processing and transmission, and its applications to computational biology as well as in wireless networking. Kannan previously received a National Institutes of Health (NIH) RO1 grant for his work on RNA sequence assembly in collaboration with Lior Pachter and David Tse. Kannan holds a Ph.D. in Electrical and Computer Engineering and a M.S. in mathematics from UIUC. He is a recipient of the Van Valkenburg outstanding graduate research award from UIUC, 2013, a co-recipient of the Qualcomm Cognitive Radio Contest first prize, 2010, a recipient of Qualcomm (CTO) Roberto Padovani outstanding intern award, 2010, a recipient of the S.V.C. Aiya (gold) medal from the Indian Institute of Science, 2008, and a co-recipient of Intel India Student Research Contest first prize, 2006.

3uweeViewNews Object
(
    [_showAnnouncements:protected] => 
    [_showTitle:protected] => 
    [showMore] => 
    [_type:protected] => spotlight
    [_from:protected] => person
    [_args:protected] => Array
        (
            [post_type] => spotlight
            [date_query] => Array
                (
                    [0] => Array
                        (
                            [after] => Array
                                (
                                    [year] => 2015
                                    [month] => 9
                                    [day] => 21
                                )

                        )

                )

            [meta_query] => Array
                (
                    [relation] => AND
                    [0] => Array
                        (
                            [key] => type
                            [value] => news
                            [compare] => LIKE
                        )

                    [1] => Array
                        (
                            [key] => subjects
                            [value] => "856"
                            [compare] => LIKE
                        )

                )

            [posts_per_page] => 6
            [post_status] => publish
        )

    [_jids:protected] => 
    [_taxa:protected] => Array
        (
        )

    [_meta:protected] => Array
        (
            [0] => Array
                (
                    [key] => type
                    [value] => news
                    [compare] => LIKE
                )

            [1] => Array
                (
                    [key] => subjects
                    [value] => "856"
                    [compare] => LIKE
                )

        )

    [_metarelation:protected] => AND
    [_results:protected] => Array
        (
            [0] => WP_Post Object
                (
                    [ID] => 11071
                    [post_author] => 12
                    [post_date] => 2017-07-21 15:42:20
                    [post_date_gmt] => 2017-07-21 22:42:20
                    [post_content] => [caption id="attachment_10222" align="alignleft" width="484"] Professor Sreeram Kannan[/caption]

UW electrical engineering Assistant Professor Sreeram Kannan leads a $1.2 million collaborative National Science Foundation (NSF) Communications and Information Foundations (CIF) Grant. The research aims to design new algorithms for sequencing DNA using nanopore readers.

Fast and inexpensive DNA sequencing technology is beginning to impact society through applications ranging from personalized medicine to the understanding of ecological systems. However, existing DNA sequencing methods are limited in the length of DNA that can be analyzed. These systems can read only short strands of DNA, limiting the ability of algorithms to resolve and analyze regions of the genome which have repeating motifs.

Nanopore sequencing is a new and emerging technology, where DNA is transmigrated through a pore, and the induced electrical current variations are measured to infer the DNA sequence. In addition to having the ability to sequence long stretches of DNA, nanopore sequencers are also relatively inexpensive and offer high mobility for testing and rapid processing of samples.

An algorithm, called base-caller, is used to infer the DNA sequence from the observed current waveform. Current base-calling methods suffer from high measurement noise. Kannan and his team of collaborators seek to address this problem. In a recent paper, they have quantified the amount of information that can be extracted by the process of nanopore sequencing, establishing interesting parallels to a classical problem studied in communication theory. A telecommunication system is mathematically characterized by the probabilistic mapping between the transmitted signal and the received signal. Analogously, the mapping between the DNA sequence and the observed current waveform can be thought of as a communication channel whose information rates can be characterized using information-theoretic methods.

This project develops a holistic approach for the nanopore sequencing problem, using tools from information theory and bio-informatics to build more representative mathematical models and better algorithms for inferring the DNA sequence, as well as to explore potential applications in DNA forensics, phasing and assembly.

Kannan is the PI on the four-year grant. Co-PIs include UW Department of Physics Professor Jens Gundlach and UCLA electrical engineering Professor Suhas Diggavi.
                    [post_title] => Professor Kannan receives NSF grant to improve groundbreaking nanopore sequencing of DNA
                    [post_excerpt] => 
                    [post_status] => publish
                    [comment_status] => closed
                    [ping_status] => closed
                    [post_password] => 
                    [post_name] => professor-kannan-receives-nsf-grant-to-improve-groundbreaking-nanopore-sequencing-of-dna
                    [to_ping] => 
                    [pinged] => 
                    [post_modified] => 2017-07-21 15:44:09
                    [post_modified_gmt] => 2017-07-21 22:44:09
                    [post_content_filtered] => 
                    [post_parent] => 0
                    [guid] => http://www.ee.washington.edu/?post_type=spotlight&p=11071
                    [menu_order] => 18
                    [post_type] => spotlight
                    [post_mime_type] => 
                    [comment_count] => 0
                    [filter] => raw
                )

            [1] => WP_Post Object
                (
                    [ID] => 10221
                    [post_author] => 12
                    [post_date] => 2017-03-23 13:55:43
                    [post_date_gmt] => 2017-03-23 20:55:43
                    [post_content] => [caption id="attachment_10222" align="alignleft" width="417"]sk_1 Assistant Professor Sreeram Kannan[/caption]

The National Science Foundation (NSF) Faculty Early Career Development (CAREER) Program offers the NSF's most prestigious awards in support of early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization. The NSF rewards these activities as they build a firm foundation for a lifetime of integrated contributions to research and education.

UW Department of Electrical Engineering Assistant Professor Sreeram Kannan received the NSF CAREER award for his work involving “Information-Theoretic Methods for RNA Analytics.” The major objective of Kannan’s research is to adapt, apply and create new information-theoretic and algorithmic methods to solve inference problems arising in RNA sequence analytics.

The last decade has seen major breakthroughs in sequencing technology. This has led not only to the ability to sequence the static aspects of the genome through DNA sequencing, but also to understand the dynamics of gene expression with transcript-level precision and single-cell resolution through RNA sequencing. This has applications in diverse areas of biology, medicine and engineering, such as evolutionary biology, developmental biology, medical transcriptomics as well as synthetic biology.

In order to leverage these advances in biotechnology, it is necessary to develop novel computational algorithms that perform inference on these new datasets. Kannan’s project will address inference problems arising at two different levels of RNA-sequencing: assembly, which deals with the inability of DNA sequencers to read long fragments of DNA, and downstream analytics, which utilizes the RNA sequence data for further biological analysis, including gene regulation and cell differentiation. Kannan’s research has a two-fold objective: to formulate and solve novel information-theoretic problems arising from genomics, as well as to apply recent algorithmic advances to this important application domain.

The project will have a significant educational component that integrates these new discoveries into graduate and undergraduate courses that can expose electrical engineering and computer science students to sequencing problems. In addition, it will engage high school and undergraduate students with this research by outreach and mentoring.

Kannan runs the Information Theory Lab, which deals with the fundamentals of information processing and transmission and its applications to computational biology as well as in wireless networking. Kannan previously received a National Institutes of Health (NIH) RO1 grant for his work on RNA sequence assembly in collaboration with Lior Pachter and David Tse. He is also the recipient of the Van Valkenburg outstanding graduate research award from the University of Illinois Urbana-Champaign, a co-recipient of the Qualcomm Cognitive Radio Contest first prize, a recipient of Qualcomm (CTO) Roberto Padovani outstanding intern award, a recipient of the S.V.C. Aiya (gold) medal from the Indian Institute of Science and a co-recipient of Intel India Student Research Contest first prize.
                    [post_title] => Professor Sreeram Kannan Receives Prestigious NSF CAREER Award
                    [post_excerpt] => 
                    [post_status] => publish
                    [comment_status] => closed
                    [ping_status] => closed
                    [post_password] => 
                    [post_name] => professor-sreeram-kannan-receives-prestigious-nsf-career-award
                    [to_ping] => 
                    [pinged] => 
                    [post_modified] => 2017-03-23 13:55:43
                    [post_modified_gmt] => 2017-03-23 20:55:43
                    [post_content_filtered] => 
                    [post_parent] => 0
                    [guid] => http://www.ee.washington.edu/?post_type=spotlight&p=10221
                    [menu_order] => 63
                    [post_type] => spotlight
                    [post_mime_type] => 
                    [comment_count] => 0
                    [filter] => raw
                )

            [2] => WP_Post Object
                (
                    [ID] => 10049
                    [post_author] => 12
                    [post_date] => 2017-02-28 13:24:49
                    [post_date_gmt] => 2017-02-28 21:24:49
                    [post_content] => [caption id="attachment_10052" align="alignleft" width="434"]nsl-perspective_team-photo_2 The UW electrical engineering research team includes (left to right) Professor and Chair Radha Poovendran, doctoral student Hossein Hosseini, Assistant Professor Baosen Zhang and Assistant Professor Sreeram Kannan (not pictured.).[/caption]

University of Washington electrical engineering researchers have shown that Google’s new machine learning-based system to identify toxic comments in online discussion forums can be bypassed by simply misspelling or adding unnecessary punctuation to abusive words, such as “idiot” or “moron.”

Perspective is a project by Google’s technology incubator Jigsaw, which uses artificial intelligence to combat internet trolls and promote more civil online discussion by automatically detecting online insults, harassment and abusive speech.  The company launched a demonstration website on Feb. 23 that allows anyone to type in a phrase and see its “toxicity score” — a measure of how rude, disrespectful or unreasonable a particular comment is.

In a paper posted Feb. 27 on the e-print repository arXiv, the UW electrical engineers and security experts demonstrated that the early stage technology system can be deceived by using common adversarial tactics. They showed one can subtly modify a phrase that receives a high toxicity score so that it contains the same abusive language but receives a low toxicity score.

Given that news platforms such as The New York Times and other media companies are exploring how the system could help curb harassment and abuse in online comment areas or social media, the UW researchers evaluated Perspective in adversarial settings. They showed that the system is vulnerable to both missing incendiary language and falsely blocking non-abusive phrases.

“Machine learning systems are generally designed to yield the best performance in benign settings. But in real-world applications, these systems are susceptible to intelligent subversion or attacks,” said senior author Radha Poovendran, chair of the UW electrical engineering department and director of the Network Security Lab. “We wanted to demonstrate the importance of designing these machine learning tools in adversarial environments. Designing a system with a benign operating environment in mind and deploying it in adversarial environments can have devastating consequences.”

To solicit feedback and invite other researchers to explore the strengths and weaknesses of using machine learning as a tool to improve online discussions, Perspective developers made their experiments, models and data publicly available along with the tool itself.

In the examples below on hot-button topics of climate change, Brexit and the recent U.S. election — which were taken directly from the Perspective API website — the UW team simply misspelled or added extraneous punctuation or spaces to the offending words, which yielded much lower toxicity scores. For example, simply changing “idiot” to “idiiot” reduced the toxicity rate of an otherwise identical comment from 84% to 20%.

nsl-google-perspective_graphic-1

In the examples below, the researchers also showed that the system does not assign a low toxicity score to a negated version of an abusive phrase.

nsl-google-perspective_graphic-2

The researchers also observed that the duplicitous changes often transfer among different phrases — once an intentionally misspelled word was given a low toxicity score in one phrase, it was also given a low score in another phrase. That means an adversary could create a “dictionary” of changes for every word and significantly simplify the attack process.

“There are two metrics for evaluating the performance of a filtering system like a spam blocker or toxic speech detector; one is the missed detection rate and the other is the false alarm rate,” said lead author and UW electrical engineering doctoral student Hossein Hosseini. “Of course scoring the semantic toxicity of a phrase is challenging, but deploying defensive mechanisms both in algorithmic and system levels can help the usability of the system in real-world settings.”

The research team suggests several techniques to improve the robustness of toxic speech detectors, including applying a spellchecking filter prior to the detection system, training the machine learning algorithm with adversarial examples and blocking suspicious users for a period of time.

“Our Network Security Lab research is typically focused on the foundations and science of cybersecurity,” said Poovendran, the lead principal investigator of a recently awarded MURI grant, of which adversarial machine learning is a significant component. “But our expanded focus includes developing robust and resilient systems for machine learning and reasoning systems that need to operate in adversarial environments for a wide range of applications.”

Co-authors include UW electrical engineering assistant professors Sreeram Kannan and Baosen Zhang.

The research is funded by the National Science Foundation, the Office of Naval Research and the Army Research Office.

More News:

[post_title] => UW Security Researchers Show that Google’s AI Platform for Defeating Internet Trolls Can be Easily Deceived [post_excerpt] => [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => uw-security-researchers-show-that-googles-ai-platform-for-defeating-internet-trolls-can-be-easily-deceived [to_ping] => [pinged] => [post_modified] => 2017-05-01 16:55:08 [post_modified_gmt] => 2017-05-01 23:55:08 [post_content_filtered] => [post_parent] => 0 [guid] => http://www.ee.washington.edu/?post_type=spotlight&p=10049 [menu_order] => 73 [post_type] => spotlight [post_mime_type] => [comment_count] => 0 [filter] => raw ) ) [_numposts:protected] => 6 [_rendered:protected] => 1 [_classes:protected] => Array ( [0] => block--spotlight-tiles ) [_finalHTML:protected] => [_postID:protected] => 856 [_errors:protected] => Array ( ) [_block:protected] => [_db:protected] => WP_Query Object ( [query] => Array ( [post_type] => spotlight [date_query] => Array ( [0] => Array ( [after] => Array ( [year] => 2015 [month] => 9 [day] => 21 ) ) ) [meta_query] => Array ( [relation] => AND [0] => Array ( [key] => type [value] => news [compare] => LIKE ) [1] => Array ( [key] => subjects [value] => "856" [compare] => LIKE ) ) [posts_per_page] => 6 [post_status] => publish ) [query_vars] => Array ( [post_type] => spotlight [date_query] => Array ( [0] => Array ( [after] => Array ( [year] => 2015 [month] => 9 [day] => 21 ) ) ) [meta_query] => Array ( [relation] => AND [0] => Array ( [key] => type [value] => news [compare] => LIKE ) [1] => Array ( [key] => subjects [value] => "856" [compare] => LIKE ) ) [posts_per_page] => 6 [post_status] => publish [error] => [m] => [p] => 0 [post_parent] => [subpost] => [subpost_id] => [attachment] => [attachment_id] => 0 [name] => [static] => [pagename] => [page_id] => 0 [second] => [minute] => [hour] => [day] => 0 [monthnum] => 0 [year] => 0 [w] => 0 [category_name] => [tag] => [cat] => [tag_id] => [author] => [author_name] => [feed] => [tb] => [paged] => 0 [meta_key] => [meta_value] => [preview] => [s] => [sentence] => [title] => [fields] => [menu_order] => [embed] => [category__in] => Array ( ) [category__not_in] => Array ( ) [category__and] => Array ( ) [post__in] => Array ( ) [post__not_in] => Array ( ) [post_name__in] => Array ( ) [tag__in] => Array ( ) [tag__not_in] => Array ( ) [tag__and] => Array ( ) [tag_slug__in] => Array ( ) [tag_slug__and] => Array ( ) [post_parent__in] => Array ( ) [post_parent__not_in] => Array ( ) [author__in] => Array ( ) [author__not_in] => Array ( ) [orderby] => menu_order [order] => ASC [ignore_sticky_posts] => [suppress_filters] => [cache_results] => 1 [update_post_term_cache] => 1 [lazy_load_term_meta] => 1 [update_post_meta_cache] => 1 [nopaging] => [comments_per_page] => 50 [no_found_rows] => ) [tax_query] => WP_Tax_Query Object ( [queries] => Array ( ) [relation] => AND [table_aliases:protected] => Array ( ) [queried_terms] => Array ( ) [primary_table] => wp_posts [primary_id_column] => ID ) [meta_query] => WP_Meta_Query Object ( [queries] => Array ( [0] => Array ( [key] => type [value] => news [compare] => LIKE ) [1] => Array ( [key] => subjects [value] => "856" [compare] => LIKE ) [relation] => AND ) [relation] => AND [meta_table] => wp_postmeta [meta_id_column] => post_id [primary_table] => wp_posts [primary_id_column] => ID [table_aliases:protected] => Array ( [0] => wp_postmeta [1] => mt1 ) [clauses:protected] => Array ( [wp_postmeta] => Array ( [key] => type [value] => news [compare] => LIKE [alias] => wp_postmeta [cast] => CHAR ) [mt1] => Array ( [key] => subjects [value] => "856" [compare] => LIKE [alias] => mt1 [cast] => CHAR ) ) [has_or_relation:protected] => ) [date_query] => WP_Date_Query Object ( [queries] => Array ( [0] => Array ( [after] => Array ( [year] => 2015 [month] => 9 [day] => 21 ) [column] => post_date [compare] => = [relation] => AND ) [column] => post_date [compare] => = [relation] => AND ) [relation] => AND [column] => wp_posts.post_date [compare] => = [time_keys] => Array ( [0] => after [1] => before [2] => year [3] => month [4] => monthnum [5] => week [6] => w [7] => dayofyear [8] => day [9] => dayofweek [10] => dayofweek_iso [11] => hour [12] => minute [13] => second ) ) [request] => SELECT SQL_CALC_FOUND_ROWS wp_posts.ID FROM wp_posts INNER JOIN wp_postmeta ON ( wp_posts.ID = wp_postmeta.post_id ) INNER JOIN wp_postmeta AS mt1 ON ( wp_posts.ID = mt1.post_id ) WHERE 1=1 AND ( wp_posts.post_date > '2015-09-21 23:59:59' ) AND ( ( wp_postmeta.meta_key = 'type' AND wp_postmeta.meta_value LIKE '%news%' ) AND ( mt1.meta_key = 'subjects' AND mt1.meta_value LIKE '%\"856\"%' ) ) AND wp_posts.post_type = 'spotlight' AND ((wp_posts.post_status = 'publish')) GROUP BY wp_posts.ID ORDER BY wp_posts.menu_order ASC LIMIT 0, 6 [posts] => Array ( [0] => WP_Post Object ( [ID] => 11071 [post_author] => 12 [post_date] => 2017-07-21 15:42:20 [post_date_gmt] => 2017-07-21 22:42:20 [post_content] => [caption id="attachment_10222" align="alignleft" width="484"] Professor Sreeram Kannan[/caption] UW electrical engineering Assistant Professor Sreeram Kannan leads a $1.2 million collaborative National Science Foundation (NSF) Communications and Information Foundations (CIF) Grant. The research aims to design new algorithms for sequencing DNA using nanopore readers. Fast and inexpensive DNA sequencing technology is beginning to impact society through applications ranging from personalized medicine to the understanding of ecological systems. However, existing DNA sequencing methods are limited in the length of DNA that can be analyzed. These systems can read only short strands of DNA, limiting the ability of algorithms to resolve and analyze regions of the genome which have repeating motifs. Nanopore sequencing is a new and emerging technology, where DNA is transmigrated through a pore, and the induced electrical current variations are measured to infer the DNA sequence. In addition to having the ability to sequence long stretches of DNA, nanopore sequencers are also relatively inexpensive and offer high mobility for testing and rapid processing of samples. An algorithm, called base-caller, is used to infer the DNA sequence from the observed current waveform. Current base-calling methods suffer from high measurement noise. Kannan and his team of collaborators seek to address this problem. In a recent paper, they have quantified the amount of information that can be extracted by the process of nanopore sequencing, establishing interesting parallels to a classical problem studied in communication theory. A telecommunication system is mathematically characterized by the probabilistic mapping between the transmitted signal and the received signal. Analogously, the mapping between the DNA sequence and the observed current waveform can be thought of as a communication channel whose information rates can be characterized using information-theoretic methods. This project develops a holistic approach for the nanopore sequencing problem, using tools from information theory and bio-informatics to build more representative mathematical models and better algorithms for inferring the DNA sequence, as well as to explore potential applications in DNA forensics, phasing and assembly. Kannan is the PI on the four-year grant. Co-PIs include UW Department of Physics Professor Jens Gundlach and UCLA electrical engineering Professor Suhas Diggavi. [post_title] => Professor Kannan receives NSF grant to improve groundbreaking nanopore sequencing of DNA [post_excerpt] => [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => professor-kannan-receives-nsf-grant-to-improve-groundbreaking-nanopore-sequencing-of-dna [to_ping] => [pinged] => [post_modified] => 2017-07-21 15:44:09 [post_modified_gmt] => 2017-07-21 22:44:09 [post_content_filtered] => [post_parent] => 0 [guid] => http://www.ee.washington.edu/?post_type=spotlight&p=11071 [menu_order] => 18 [post_type] => spotlight [post_mime_type] => [comment_count] => 0 [filter] => raw ) [1] => WP_Post Object ( [ID] => 10221 [post_author] => 12 [post_date] => 2017-03-23 13:55:43 [post_date_gmt] => 2017-03-23 20:55:43 [post_content] => [caption id="attachment_10222" align="alignleft" width="417"]sk_1 Assistant Professor Sreeram Kannan[/caption] The National Science Foundation (NSF) Faculty Early Career Development (CAREER) Program offers the NSF's most prestigious awards in support of early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization. The NSF rewards these activities as they build a firm foundation for a lifetime of integrated contributions to research and education. UW Department of Electrical Engineering Assistant Professor Sreeram Kannan received the NSF CAREER award for his work involving “Information-Theoretic Methods for RNA Analytics.” The major objective of Kannan’s research is to adapt, apply and create new information-theoretic and algorithmic methods to solve inference problems arising in RNA sequence analytics. The last decade has seen major breakthroughs in sequencing technology. This has led not only to the ability to sequence the static aspects of the genome through DNA sequencing, but also to understand the dynamics of gene expression with transcript-level precision and single-cell resolution through RNA sequencing. This has applications in diverse areas of biology, medicine and engineering, such as evolutionary biology, developmental biology, medical transcriptomics as well as synthetic biology. In order to leverage these advances in biotechnology, it is necessary to develop novel computational algorithms that perform inference on these new datasets. Kannan’s project will address inference problems arising at two different levels of RNA-sequencing: assembly, which deals with the inability of DNA sequencers to read long fragments of DNA, and downstream analytics, which utilizes the RNA sequence data for further biological analysis, including gene regulation and cell differentiation. Kannan’s research has a two-fold objective: to formulate and solve novel information-theoretic problems arising from genomics, as well as to apply recent algorithmic advances to this important application domain. The project will have a significant educational component that integrates these new discoveries into graduate and undergraduate courses that can expose electrical engineering and computer science students to sequencing problems. In addition, it will engage high school and undergraduate students with this research by outreach and mentoring. Kannan runs the Information Theory Lab, which deals with the fundamentals of information processing and transmission and its applications to computational biology as well as in wireless networking. Kannan previously received a National Institutes of Health (NIH) RO1 grant for his work on RNA sequence assembly in collaboration with Lior Pachter and David Tse. He is also the recipient of the Van Valkenburg outstanding graduate research award from the University of Illinois Urbana-Champaign, a co-recipient of the Qualcomm Cognitive Radio Contest first prize, a recipient of Qualcomm (CTO) Roberto Padovani outstanding intern award, a recipient of the S.V.C. Aiya (gold) medal from the Indian Institute of Science and a co-recipient of Intel India Student Research Contest first prize. [post_title] => Professor Sreeram Kannan Receives Prestigious NSF CAREER Award [post_excerpt] => [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => professor-sreeram-kannan-receives-prestigious-nsf-career-award [to_ping] => [pinged] => [post_modified] => 2017-03-23 13:55:43 [post_modified_gmt] => 2017-03-23 20:55:43 [post_content_filtered] => [post_parent] => 0 [guid] => http://www.ee.washington.edu/?post_type=spotlight&p=10221 [menu_order] => 63 [post_type] => spotlight [post_mime_type] => [comment_count] => 0 [filter] => raw ) [2] => WP_Post Object ( [ID] => 10049 [post_author] => 12 [post_date] => 2017-02-28 13:24:49 [post_date_gmt] => 2017-02-28 21:24:49 [post_content] => [caption id="attachment_10052" align="alignleft" width="434"]nsl-perspective_team-photo_2 The UW electrical engineering research team includes (left to right) Professor and Chair Radha Poovendran, doctoral student Hossein Hosseini, Assistant Professor Baosen Zhang and Assistant Professor Sreeram Kannan (not pictured.).[/caption]

University of Washington electrical engineering researchers have shown that Google’s new machine learning-based system to identify toxic comments in online discussion forums can be bypassed by simply misspelling or adding unnecessary punctuation to abusive words, such as “idiot” or “moron.”

Perspective is a project by Google’s technology incubator Jigsaw, which uses artificial intelligence to combat internet trolls and promote more civil online discussion by automatically detecting online insults, harassment and abusive speech.  The company launched a demonstration website on Feb. 23 that allows anyone to type in a phrase and see its “toxicity score” — a measure of how rude, disrespectful or unreasonable a particular comment is.

In a paper posted Feb. 27 on the e-print repository arXiv, the UW electrical engineers and security experts demonstrated that the early stage technology system can be deceived by using common adversarial tactics. They showed one can subtly modify a phrase that receives a high toxicity score so that it contains the same abusive language but receives a low toxicity score.

Given that news platforms such as The New York Times and other media companies are exploring how the system could help curb harassment and abuse in online comment areas or social media, the UW researchers evaluated Perspective in adversarial settings. They showed that the system is vulnerable to both missing incendiary language and falsely blocking non-abusive phrases.

“Machine learning systems are generally designed to yield the best performance in benign settings. But in real-world applications, these systems are susceptible to intelligent subversion or attacks,” said senior author Radha Poovendran, chair of the UW electrical engineering department and director of the Network Security Lab. “We wanted to demonstrate the importance of designing these machine learning tools in adversarial environments. Designing a system with a benign operating environment in mind and deploying it in adversarial environments can have devastating consequences.”

To solicit feedback and invite other researchers to explore the strengths and weaknesses of using machine learning as a tool to improve online discussions, Perspective developers made their experiments, models and data publicly available along with the tool itself.

In the examples below on hot-button topics of climate change, Brexit and the recent U.S. election — which were taken directly from the Perspective API website — the UW team simply misspelled or added extraneous punctuation or spaces to the offending words, which yielded much lower toxicity scores. For example, simply changing “idiot” to “idiiot” reduced the toxicity rate of an otherwise identical comment from 84% to 20%.

nsl-google-perspective_graphic-1

In the examples below, the researchers also showed that the system does not assign a low toxicity score to a negated version of an abusive phrase.

nsl-google-perspective_graphic-2

The researchers also observed that the duplicitous changes often transfer among different phrases — once an intentionally misspelled word was given a low toxicity score in one phrase, it was also given a low score in another phrase. That means an adversary could create a “dictionary” of changes for every word and significantly simplify the attack process.

“There are two metrics for evaluating the performance of a filtering system like a spam blocker or toxic speech detector; one is the missed detection rate and the other is the false alarm rate,” said lead author and UW electrical engineering doctoral student Hossein Hosseini. “Of course scoring the semantic toxicity of a phrase is challenging, but deploying defensive mechanisms both in algorithmic and system levels can help the usability of the system in real-world settings.”

The research team suggests several techniques to improve the robustness of toxic speech detectors, including applying a spellchecking filter prior to the detection system, training the machine learning algorithm with adversarial examples and blocking suspicious users for a period of time.

“Our Network Security Lab research is typically focused on the foundations and science of cybersecurity,” said Poovendran, the lead principal investigator of a recently awarded MURI grant, of which adversarial machine learning is a significant component. “But our expanded focus includes developing robust and resilient systems for machine learning and reasoning systems that need to operate in adversarial environments for a wide range of applications.”

Co-authors include UW electrical engineering assistant professors Sreeram Kannan and Baosen Zhang.

The research is funded by the National Science Foundation, the Office of Naval Research and the Army Research Office.

More News:

[post_title] => UW Security Researchers Show that Google’s AI Platform for Defeating Internet Trolls Can be Easily Deceived [post_excerpt] => [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => uw-security-researchers-show-that-googles-ai-platform-for-defeating-internet-trolls-can-be-easily-deceived [to_ping] => [pinged] => [post_modified] => 2017-05-01 16:55:08 [post_modified_gmt] => 2017-05-01 23:55:08 [post_content_filtered] => [post_parent] => 0 [guid] => http://www.ee.washington.edu/?post_type=spotlight&p=10049 [menu_order] => 73 [post_type] => spotlight [post_mime_type] => [comment_count] => 0 [filter] => raw ) ) [post_count] => 3 [current_post] => -1 [in_the_loop] => [post] => WP_Post Object ( [ID] => 11071 [post_author] => 12 [post_date] => 2017-07-21 15:42:20 [post_date_gmt] => 2017-07-21 22:42:20 [post_content] => [caption id="attachment_10222" align="alignleft" width="484"] Professor Sreeram Kannan[/caption] UW electrical engineering Assistant Professor Sreeram Kannan leads a $1.2 million collaborative National Science Foundation (NSF) Communications and Information Foundations (CIF) Grant. The research aims to design new algorithms for sequencing DNA using nanopore readers. Fast and inexpensive DNA sequencing technology is beginning to impact society through applications ranging from personalized medicine to the understanding of ecological systems. However, existing DNA sequencing methods are limited in the length of DNA that can be analyzed. These systems can read only short strands of DNA, limiting the ability of algorithms to resolve and analyze regions of the genome which have repeating motifs. Nanopore sequencing is a new and emerging technology, where DNA is transmigrated through a pore, and the induced electrical current variations are measured to infer the DNA sequence. In addition to having the ability to sequence long stretches of DNA, nanopore sequencers are also relatively inexpensive and offer high mobility for testing and rapid processing of samples. An algorithm, called base-caller, is used to infer the DNA sequence from the observed current waveform. Current base-calling methods suffer from high measurement noise. Kannan and his team of collaborators seek to address this problem. In a recent paper, they have quantified the amount of information that can be extracted by the process of nanopore sequencing, establishing interesting parallels to a classical problem studied in communication theory. A telecommunication system is mathematically characterized by the probabilistic mapping between the transmitted signal and the received signal. Analogously, the mapping between the DNA sequence and the observed current waveform can be thought of as a communication channel whose information rates can be characterized using information-theoretic methods. This project develops a holistic approach for the nanopore sequencing problem, using tools from information theory and bio-informatics to build more representative mathematical models and better algorithms for inferring the DNA sequence, as well as to explore potential applications in DNA forensics, phasing and assembly. Kannan is the PI on the four-year grant. Co-PIs include UW Department of Physics Professor Jens Gundlach and UCLA electrical engineering Professor Suhas Diggavi. [post_title] => Professor Kannan receives NSF grant to improve groundbreaking nanopore sequencing of DNA [post_excerpt] => [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => professor-kannan-receives-nsf-grant-to-improve-groundbreaking-nanopore-sequencing-of-dna [to_ping] => [pinged] => [post_modified] => 2017-07-21 15:44:09 [post_modified_gmt] => 2017-07-21 22:44:09 [post_content_filtered] => [post_parent] => 0 [guid] => http://www.ee.washington.edu/?post_type=spotlight&p=11071 [menu_order] => 18 [post_type] => spotlight [post_mime_type] => [comment_count] => 0 [filter] => raw ) [comment_count] => 0 [current_comment] => -1 [found_posts] => 3 [max_num_pages] => 1 [max_num_comment_pages] => 0 [is_single] => [is_preview] => [is_page] => [is_archive] => 1 [is_date] => [is_year] => [is_month] => [is_day] => [is_time] => [is_author] => [is_category] => [is_tag] => [is_tax] => [is_search] => [is_feed] => [is_comment_feed] => [is_trackback] => [is_home] => [is_404] => [is_embed] => [is_paged] => [is_admin] => [is_attachment] => [is_singular] => [is_robots] => [is_posts_page] => [is_post_type_archive] => 1 [query_vars_hash:WP_Query:private] => e53a79e7a4bc222c53984e1f9b35b74e [query_vars_changed:WP_Query:private] => 1 [thumbnails_cached] => [stopwords:WP_Query:private] => [compat_fields:WP_Query:private] => Array ( [0] => query_vars_hash [1] => query_vars_changed ) [compat_methods:WP_Query:private] => Array ( [0] => init_query_flags [1] => parse_tax_query ) ) )
 

Associated Labs

Research Areas

Education

  • Ph.D. Electrical and Computing Engineering, 2012
    University of Illinois at Urbana-Champaign
  • M.S. Mathematics, 2012
    University of Illinois at Urbana-Champaign
  • M.E. Telecommunications, 2008
    Indian Institute of Science, India
  • B.E. Electronics and Communication, 2006
    Anna University, India