Sotabase

Career

· Researcher (co-author of AI self-recognition study), Columbia University2025–
· Associate Professor, University of Washington, Information School
· Adjunct Assistant Professor, University of Washington, Paul G. Allen School of Computer Science & Engineering

Publications (53)

Semantics derived automatically from language corpora contain human-like biases
Science · 2016
2,964
cited
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Conference on Fairness, Accountability and Transparency · 2022
436
cited
Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases
AAAI/ACM Conference on AI, Ethics, and Society · 2020
272
cited
De-anonymizing Programmers via Code Stylometry
USENIX Security Symposium · 2015
224
cited
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Conference on Fairness, Accountability and Transparency · 2020
173
cited
Doppelgänger Finder: Taking Stylometry to the Underground
IEEE Symposium on Security and Privacy · 2014
140
cited
When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries
Network and Distributed System Security Symposium · 2015
121
cited
Use Fewer Instances of the Letter "i": Toward Writing Style Anonymization
International Symposium on Privacy Enhancing Technologies · 2012
108
cited
ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages
International Computing Education Research Workshop · 2023
105
cited
Privacy Detective: Detecting Private Information and Collective Privacy Behavior in a Large Social Network
Workshop on Privacy in the Electronic Society · 2014
91
cited
Historical representations of social groups across 200 years of word embeddings from Google Books
Proceedings of the National Academy of Sciences of the United States of America · 2022
84
cited
Approaches to adversarial drift
Security and Artificial Intelligence · 2013
82
cited
Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks
Conference on Fairness, Accountability and Transparency · 2023
75
cited
Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
Conference on Fairness, Accountability and Transparency · 2022
73
cited
Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics
AAAI/ACM Conference on AI, Ethics, and Society · 2022
72
cited
Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms
AAAI/ACM Conference on AI, Ethics, and Society · 2020
67
cited
American == White in Multimodal Language-and-Image AI
AAAI/ACM Conference on AI, Ethics, and Society · 2022
57
cited
Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models
Conference on Empirical Methods in Natural Language Processing · 2021
56
cited
Git Blame Who?: Stylistic Authorship Attribution of Small, Incomplete Source Code Fragments
International Conference on Software Engineering · 2017
48
cited
Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach
AAAI/ACM Conference on AI, Ethics, and Society · 2024
46
cited
Sotabase
Aylin Caliskan | Researcher Profile | Sotabase | Sotabase