Audience Tools

Affiliate Position

  • Adjunct Assistant Professor, University of Washington Paul G. Allen School of Computer Science & Engineering

Specializations

  • Artificial Intelligence, Bias, and Ethics
  • Machine Learning, Natural Language Processing, and Computer Vision
  • Computational Social Science

Research Areas

Courses

Biography

Aylin Caliskan is an Assistant Professor at the University of Washington Information School and an Adjunct Assistant Professor at the Paul G. Allen School of Computer Science and Engineering. Previously, Caliskan was an Assistant Professor of Computer Science at George Washington University. Caliskan studies the underpinning mechanisms of information transfer between human society and artificial intelligence (AI). Specifically, Caliskan's research interests lie in AI ethics, AI bias, computer vision, natural language processing, and machine learning. By developing transparency enhancing algorithms that detect and quantify human-like associations and biases learned by machines, Caliskan investigates the reasoning behind AI representations and decisions. Caliskan's publication in Science demonstrated how semantics derived from language corpora contain human-like biases. Her work on machine learning's impact on fairness and privacy received the best talk and best paper awards, and she was selected as a Rising Star in EECS at Stanford University. Caliskan holds a Ph.D. in Computer Science from Drexel University's College of Computing & Informatics and a Master of Science in Robotics from the University of Pennsylvania. Caliskan was a Postdoctoral Researcher and a Fellow at Princeton University's Center for Information Technology Policy. Caliskan was named a Nonresident Fellow in Governance Studies at the Brookings Institution in 2021, and in 2023, she was recognized as one of the 100 Brilliant Women in AI Ethics and honored with an IJCAI Early Career Spotlight.

Awards

  • 100 Brilliant Women in AI Ethics - Women in AI Ethics, 2023
  • IJCAI Early Career Spotlight - International Joint Conference on Artificial Intelligence, 2023
  • Nonresident Fellow in Governance Studies at the Center for Technology Innovation - Brookings Institution, 2021
  • Rising Star in EECS (Electrical Engineering and Computer Science) - Stanford University, 2017
  • Best Talk Award for A Story of Discrimination and Unfairness: Implicit Bias Embedded in Language Models - HotPETS, 2016
  • Teaching Assistant Excellence Award Nominee - Drexel University, 2015
  • Inaugural College of Computing & Informatics Day PhD Poster Award - Drexel University, 2014
  • Travel Award - IEEE Symposium on Security and Privacy, 2014
  • Brocade Scholarship - Grace Hopper Celebration of Women in Computing, 2013
  • Executive Council Award - Upsilon Pi Epsilon, 2013
  • Andreas Pfitzmann Best Student Paper Award - Privacy Enhancing Technologies Symposium (PETS), 2012
  • International Honor Society in the Computing and Information Disciplines - Upsilon Pi Epsilon, 2012
  • Xerox Scholarship - Grace Hopper Celebration of Women in Computing, 2012

Publications and Contributions

  • Conference Paper
    Artificial Intelligence, Bias, and Ethics (2023)
    The 32nd International Joint Conference on Artificial Intelligence (IJCAI) Author: Aylin Caliskan
  • Conference Paper
    Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks (2023)
    The 2023 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) Authors: Xiaoying (Katelyn) Mei, Sonia Fereidooni, Aylin Caliskan
  • Conference Paper
    ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages (2023)
    AAAI/ACM Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES) Authors: Sourojit Ghosh, Aylin Caliskan
  • Conference Paper
    Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias (2023)
    The 2023 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) Authors: Robert Wolfe, Yiwei Yang, William G Howe, Aylin Caliskan
  • Conference Paper
    Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale (2023)
    The 2023 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) Authors: Federico Bianchi, Pratyusha Kalluri, Esin Durmus, Faisal Ladhak, Myra Cheng, Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan
  • Conference Paper
    Evaluating Biased Attitude Associations of Language Models in an Intersectional Context (2023)
    AAAI/ACM Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES) Authors: Shiva Omrani Sabbaghi, Robert Wolfe, Aylin Caliskan
  • Conference Poster
    Regularizing Model Gradients with Concepts to Improve Robustness to Spurious Correlations (2023)
    Fortieth International Conference on Machine Learning Workshop on Spurious Correlations, Invariance, and Stability (ICML SCIS 2023) Authors: Yiwei Yang, Anthony Zhe Liu, Robert Wolfe, Aylin Caliskan, William G Howe
  • Conference Paper
    American == White in Multimodal Language-and-Image AI (2022)
    AAAI/ACM Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES) Authors: Robert Wolfe, Aylin Caliskan
  • Comments
    Comments to the Federal Trade Commission re: Commercial Surveillance ANPR, R111004 (2022)
    Federal Trade Commission 2022 Authors: Clara Berridge, Aylin Caliskan, Ryan Calo, Mary D. Fan, Alexis Hiniker, Tadayoshi Kohno, Franziska Roesner
  • Conference Paper
    Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations (2022)
    60th Annual Meeting of the Association for Computational Linguistics (ACL), 2022 Authors: Robert Wolfe, Aylin Caliskan
  • Conference Paper
    Detecting Emerging Associations and Behaviors With Regional and Diachronic Word Embeddings (2022)
    16th IEEE International Conference on Semantic Computing (ICSC 2022) Authors: Robert Wolfe, Aylin Caliskan
  • Conference Paper
    Evidence for Hypodescent in Visual Semantic AI (2022)
    ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2022 Authors: Robert Wolfe, Mahzarin Bahaji, Aylin Caliskan
  • Conference Paper
    Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics (2022)
    AAAI/ACM Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES) Authors: Aylin Caliskan, Pimparkar Parth Ajay, Tessa Charlesworth, Robert Wolfe, Mahzarin R Banaji
  • Journal Article, Academic Journal
    Historical Representations of Social Groups Across 200 Years of Word Embeddings from Google Books (2022)
    Proceedings of the National Academy of Sciences (PNAS 2022) Authors: Tessa Charlesworth, Aylin Caliskan, Mahzarin R Banaji
  • Conference Paper
    Learning to Behave: Improving Covert Channel Security with Behavior-Based Design (2022)
    The 22nd Privacy Enhancing Technologies Symposium (PETS), 2022 Authors: Aylin Caliskan, Ryan Wails, Andrew Stange, Samantha Troper, Roger Dingledine, Rob Jansen, Micah Sherr
  • Policy piece
    Managing the risks of inevitably biased visual artificial intelligence systems (2022)
    The Brookings Institution 2022 Authors: Aylin Caliskan, Ryan Steed
  • Conference Paper
    Markedness in Visual Semantic AI (2022)
    ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2022 Authors: Robert Wolfe, Aylin Caliskan
  • Conference Paper
    Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals (2022)
    AAAI/ACM Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES) Authors: Shiva Omrani Sabbaghi, Aylin Caliskan
  • Conference Paper
    VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models (2022)
    Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022) Authors: Robert Wolfe, Aylin Caliskan
  • Journal Article, Academic Journal
    A Set of Maximally Distinct Facial Traits Learned by Machines is not Predictive of Appearance Bias in the Wild (2021)
    AI and Ethics Authors: Ryan Steed, Aylin Caliskan
  • Conference Paper
    Automatically Characterizing Targeted Information Operations Through Biases Present in Discourse on Twitter (2021)
    IEEE International Conference on Semantic Computing (ICSC) Authors: Autumn Toney, Ashkat Pandey, David Broniatowski, Wei Guo, Aylin Caliskan
  • Report
    Comments in Response to ‘A Proposal for Identifying and Managing Bias in Artificial Intelligence’ from the National Institute of Standards and Technology (2021)
    Draft NIST Special Publication 1270 Authors: Aylin Caliskan, Bernease Herman, Emily M. Bender
  • Comments with American Psychological Association (APA) in response to the The National Science Foundation (NSF) and the White House Office of Science and Technology Policy (OSTP) Request for Information (RFI) on an Implementation Plan for a National Artificial Intelligence Research Resource (NAIRR) (2021)
    Author: Aylin Caliskan
  • Conference Paper
    Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases (2021)
    AAAI/ACM Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES) Authors: Wei Guo, Aylin Caliskan
  • Report
    Detecting and mitigating bias in natural language processing (2021)
    The Brookings Institution Author: Aylin Caliskan
  • Conference Paper
    Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy’s Price Discrimination Algorithms (2021)
    AAAI/ACM Artificial Intelligence, Ethics, and Society (AAAI/ACM AIES) Authors: Akshat Pandey, Aylin Caliskan
  • Conference Paper
    Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases (2021)
    ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) Authors: Ryan Steed, Aylin Caliskan
  • Conference Paper
    Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models (2021)
    Empirical Methods in Natural Language Processing (EMNLP) Authors: Robert Wolfe , Aylin Caliskan
  • Book, Chapter in Non-Scholarly Book-New
    Social Biases in Word Embeddings and Their Relation to Human Cognition (2021)
    The Atlas of Language Analysis in Psychology Authors: Aylin Caliskan, Molly Lewis Editors: Morteza Deghani, Ryan Boyd
  • Conference Paper
    ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries (2021)
    Empirical Methods in Natural Language Processing (EMNLP) Authors: Autumn Toney-Wails, Aylin Caliskan
  • Conference Paper
    If I Tap It, Will They Come? An Introductory Analysis of Fairness in a Large-Scale Ride Hailing Dataset (2020)
    Academy of Marketing Science Annual Conference (AMS) Authors: Aylin Caliskan, Begum Kaplan
  • Docket
    Comments in response to the National Institute of Standards and Technology Request for Information on Developing a Federal AI Standards Engagement Plan (2019)
    National Institute of Standards and Technology (NIST) Authors: David Broniatowski, Aylin Caliskan, Valerie Reyna, Reva Schwartz
  • Conference Paper
    Git Blame Who?: Stylistic Authorship Attribution of Small, Incomplete Source Code Fragments (2019)
    Privacy Enhancing Technologies Symposium (PETS) Authors: Edwin Dauber, Aylin Caliskan, Michael Weisman, Richard Harang, Gregory Schrearer, Frederica Nelson, Rachel Greenstadt
  • Conference Poster
    Privacy and Security via Machine Learning and Natural Language Processing. (2018)
    Cybersecurity Retreat, Princeton University Author: Aylin Caliskan
  • Conference Paper
    Stylistic authorship attribution of small, incomplete source code fragments Authors. (2018)
    IEEE/ACM 40th International Conference on Software Engineering: Companion Authors: Edwin Dauber, Aylin Caliskan, Richard Harang, Rachel Greenstadt
  • Journal Article, Academic Journal
    Stylometry of Author-Specific and Country-Specific Style Features in JavaScript. (2018)
    Network and Distributed System Security Symposium (NDSS) Authors: Dennis Rollke, Aviel J. Stein, Edwin Daub, Mosfiqur Rahman, Michael J. Weisman, Gregory G. Shearer, Frederica Nelson, Aylin Caliskan, Richard Harang, Rachel Greenstadt
  • Conference Paper
    When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries (2018)
    Network and Distributed System Security Symposium (NDSS) Authors: Aylin Caliskan, Fabian Yamaguchi, Edwin Dauber, Richard Harang, Konrad Rieck, Arvind Narayanan
  • Journal Article, Academic Journal
    Semantics derived automatically from language corpora contain human-like biases (2017)
    Science Authors: Aylin Caliskan, Joanna J. Bryson, Arvind Narayanan
  • Conference Paper
    A Story of Discrimination and Unfairness (2016)
    Hot Topics in Privacy Enhancing Technologies (HotPETs) Authors: Aylin Caliskan, Joanna J. Bryson, Arvind Narayanan
  • Conference Paper
    De-anonymizing Programmers via Code Stylometry (2015)
    USENIX Security Symposium (USENIX Security) Authors: Aylin Caliskan, Richard Harang, Andrew Liu, Fabian Yamaguchi, Arvind Narayanan, Clare Voss, Rachel Greenstadt
  • Conference Paper
    How do we decide how much to reveal? (Hint: Our privacy behavior might be socially constructed.) (2015)
    Special Issue on Security, Privacy, and Human Behavior, ACM Computers & Society Author: Aylin Caliskan
  • Conference Paper
    Doppelgänger Finder: Taking Stylometry To The Underground (2014)
    IEEE Symposium on Security and Privacy Authors: Sadia Afroz, Aylin Caliskan, Ariel Stolerman, Rachel Greenstadt, Damon McCoy
  • Conference Workshop Paper
    Privacy Detective: Detecting Private Information and Collective Privacy Behavior in a Large Social Network (2014)
    Workshop on Privacy in the Electronic Society (WPES) Authors: Aylin Caliskan, Jonathan Walsh, Rachel Greenstadt
  • Conference Workshop Paper
    Approaches to Adversarial Drift (2013)
    ACM Workshop on Artificial Intelligence and Security (AISec) Authors: Alex Kantchelian, Sadia Afroz, Ling Huang, Aylin Caliskan, Brad Miller, Michael Carl Tschantz, Anthony Joseph, J. D. Tygar
  • Conference Workshop Paper
    From Language to Family and Back: Native Language and Language Family Identification from English Text (2013)
    Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop (NAACL-SRW) Authors: Aylin Caliskan, Rachel Greenstadt
  • Conference Workshop Paper
    How Privacy Flaws Affect Consumer Perception (2013)
    3rd Workshop on Socio-Technical Aspects in Security and Trust (STAST) Authors: Aylin Caliskan, Jordan Santell, Aaron Chapin, Rachel Greenstadt
  • Conference Paper
    Translate once, translate twice, translate thrice and attribute: Identifying authors and machine translation tools in translated text (2012)
    IEEE International Conference on Semantic Computing (ICSC) Authors: Aylin Caliskan, Rachel Greenstadt
  • Conference Paper
    Use Fewer Instances of the Letter “i”: Toward Writing Style Anonymization (2012)
    Privacy Enhancing Technologies Symposium (PETS) Authors: Andrew McDonald, Sadia Afroz, Aylin Caliskan, Ariel Stolerman, Rachel Greenstadt
  • Conference Poster
    ENVOY: Exploration and Navigation Vehicle for geolOgY (2011)
    University of Pennsylvania’s Entry in NASA/NIA RASC-AL Space Exploration Competition - Innovation in robotics to operate on the Moon, Mars, and beyond. Authors: Arunkumar Byravan, Aylin Caliskan, Jonas Cleveland, Daniel Gilles, Jaimeen Kapadia, , Theparit Peerasathien, Bharath Sankaran, Alex Tozzo
  • Conference Poster
    NA
    Authors: Inyoung Cheong, Aylin Caliskan, Tadayoshi Kohno

Presentations

  • Artificial Intelligence, Bias, and Ethics (2023)
    Stanford University - Palo Alto, CA
  • Special Session on Assessing and Mitigating AI Bias in Speech Processing Systems (2023)
    INTERSPEECH 2023 - Dublin, Ireland
  • AI + Society & Health Panel Moderator (2022)
    AI@UW - Seattle, WA
  • Briefing on Understanding and Addressing Racial Bias in Facial Recognition (2022)
    The National Academy of Sciences - Washington, DC
  • Gender Bias in Word Embeddings (2022)
    Santa Fe Institute Conference: Language as a Window into Mind and Society - Santa Fe, NM
  • Gender Bias in Word Embeddings (2022)
    University of Chicago - Chicago, IL
  • Language as a Window into Mind and Society (2022)
    Santa Fe Institute - Santa Fe, NM
  • Quantifying Biases and Societal Defaults in Word Embeddings and Language-Vision AI (2022)
    The National Institute of Standards and Technology (NIST), Artificial Intelligence Measurement and Evaluation Colloquia - Virtual
  • Sexual Objectification of Women and Girls in Implicit Machine Cognition (2022)
    Stanford University - Palo Alto, CA
  • Transparency in Algorithmic Bias (2022)
    Santa Fe Institute Workshop: Can Algorithms Bend the Arc Toward Justice? - Santa Fe, NM
  • Artificial Intelligence for Social Good: When Machines Learn Human-like Biases from Data (2021)
    Harvard University, University of Chicago, University of Washington, Ninth Circuit’s Fairness Committee - Zoom
  • Workshop on AI on Artificial Intelligence in Information Research and Practice (2021)
    ASIS&T 2021 - Salt Lake City, Utah
  • Algorithmic Measures of Language Mirror Human Biases (2020)
    Georgetown University - Washington, DC
  • Algorithmic Measures of Language Mirror Human Biases and Widely Shared Associations (2020)
    Santa Fe Institute - Santa Fe, NM
  • Bias and AI Ethics (2020)
    DefCon28 AI Village - Virtual
  • Bias in AI (2020)
    NIST AI Workshop - Virtual
  • Bias in AI and Digital Humanities (2020)
    University of Pennsylvania - Philadelphia, PA
  • Gender Breakthrough (2020)
    AI for Good Global Summit - Geneva, Switzerland
  • Gender Equity (2020)
    AI for Good Global Summit - Geneva, Switzerland
  • Implications of Biased AI on Democracy, Equity, and Justice (2020)
    COLING Workshop on Natural Language Processing for Internet Freedom - Virtual
  • Promises and Pitfalls of Big Data Approaches to Intersectional Equity in STEM (2020)
    NSF Workshop - NSF Workshop
  • AI for Social Good, Bias and Ethics Panel (2019)
    WeCNLP Summit at Facebook - Menlo Park, CA
  • Algorithmic Measures of Language Mirror Human Biases (2019)
    Symposium on Computer-Resident Language and Naturalistic Conversation as Windows Into Social Cognition - Santa Fe, NM
  • Algorithmic Mirrors of Human Biases (2019)
    Virginia Tech - Blacksburg, Virginia
  • Algorithmic Mirrors of Human Biases (2019)
    University of Chicago - Chicago, IL
  • Algorithmic Mirrors of Society (2019)
    University of Maryland - College Park, Maryland
  • Bias in AI (2019)
    Social Science Foo Camp at Facebook - Menlo Park, CA
  • Hands-on Tutorial: AI Fairness 360 (2019)
    ACM Conference on Fairness, Accountability, and Transparency (ACM FAT*) - Atlanta, GA
  • Human-like Bias in Machine Intelligence (2019)
    SEH WOW Talk, George Washington University - Washington, D.C.
  • Monitoring Hate Speech in the US Media (2019)
    Workshop on Defining, Monitoring and Countering Hate Speech, George Washington University, School of Media and Public Affairs - Washington, D.C.
  • Neural Networks for NLP (2019)
    George Washington University - Washington, D.C.
  • NSF Workshop: Fairness, Ethics, Accountability, and Transparency (FEAT) (2019)
    NSF Workshop - Atlanta, GA
  • Tutorial on Distributional Semantics via Word Embeddings (2019)
    Department of Psychology, Harvard University - Cambridge, MA
  • AI & Equity (2018)
    MIT Media Lab - Cambridge, MA
  • Bias in Machine Learning (2018)
    ACM & Women in Computer Science at GWU - Washington D.C.
  • De-anonymizing Programmers from Source Code and Binaries (2018)
    DEFCON - Las Vegas, NV
  • The Great Power of AI: Algorithmic Mirrors of Individuals and Society (2018)
    Brown University, Duke University, ETH Zurich, George Washington University, Tufts University, University of Maryland, University of Virginia, and Yale University - Brown University, Duke University, ETH Zurich, George Washington University, Tufts University, University of Maryland, University of Virginia, and Yale University
  • The Great Power of AI: Algorithmic Mirrors of Society (2018)
    DEFCON - Las Vegas, NV
  • Beyond Big Data: What Can We Learn from AI Models? (2017)
    AISec - CCS Workshop - Dallas, TX
  • A Story of Discrimination and Unfairness: Implicit Bias Embedded in Language Models (2016)
    HotPETS 2016 - PETS - Darmstadt, Germany
  • De-anonymizing Programmers and Code Stylometry - Large Scale Authorship Attribution from Source Code and Executable Binaries of Compiled Code (2016)
    Princeton University CITP Luncheon Speaker Series - Princeton, NJ
  • Natural Language Processing and Privacy: A Double Edged Sword (2016)
    Infer - PETS Workshop - Infer - PETS Workshop
  • Code Stylometry and Programmer De-anonymization (2015)
    University of Göttingen - Göttingen, Germany
  • De-anonymizing Programmers (2015)
    32C3 - Chaos Communication Congress - Hamburg, Germany
  • De-anonymizing Programmers via Code Stylometry (2015)
    Cornell Systems Lunch - Ithaca, NY
  • Support Vector Machines, Kernel Methods, Random Forests, and Feature Projection (2015)
    CS613-Machine Learning (Drexel University) - Philadelphia, PA
  • Security Review of Digital Privacy and the Underground: Miscreant Activity in the Internet Guest Lecture (2014)
    CS475-Computer and Network Security (Drexel University) - Philadelphia, PA
  • Source Code and Cross-Domain Stylometry (2014)
    31st Chaos Communication Congress - Hamburg, Germany
  • Stylometry and Online Underground Markets (2012)
    29th Chaos Communication Congress - Hamburg, Germany
  • Quantifying the Translator Effect: Identifying authors and machine translation tools in translated text (2011)
    Girl Geek Dinners Philly - Philadelphia, PA