Aylin Caliskan

Orcid: 0000-0001-7154-8629

According to our database1, Aylin Caliskan authored at least 55 papers between 2012 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
"I don't see myself represented here at all": User Experiences of Stable Diffusion Outputs Containing Representational Harms across Gender Identities and Nationalities.
CoRR, 2024

A Taxonomy of Stereotype Content in Large Language Models.
CoRR, 2024

Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval.
CoRR, 2024

Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach.
CoRR, 2024

Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis.
CoRR, 2024

ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor.
CoRR, 2024

Global Gallery: The Fine Art of Painting Culture Portraits through Multilingual Instruction Tuning.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

BiasDora: Exploring Hidden Biased Associations in Vision-Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Label-Efficient Group Robustness via Out-of-Distribution Concept Curation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Traversable Wormhole in f(Q) Gravity Using Conformal Symmetry.
Symmetry, March, 2023

Is the U.S. Legal System Ready for AI's Challenges to Human Values?
CoRR, 2023

Artificial Intelligence, Bias, and Ethics.
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias.
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023

Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks.
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale.
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023

Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Evaluating Biased Attitude Associations of Language Models in an Intersectional Context.
Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023

ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages.
Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023

2022
Learning to Behave: Improving Covert Channel Security with Behavior-Based Designs.
Proc. Priv. Enhancing Technol., 2022

Detecting Emerging Associations and Behaviors With Regional and Diachronic Word Embeddings.
Proceedings of the 16th IEEE International Conference on Semantic Computing, 2022

Markedness in Visual Semantic AI.
Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

Evidence for Hypodescent in Visual Semantic AI.
Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

American == White in Multimodal Language-and-Image AI.
Proceedings of the AIES '22: AAAI/ACM Conference on AI, Ethics, and Society, Oxford, United Kingdom, May 19, 2022

Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals.
Proceedings of the AIES '22: AAAI/ACM Conference on AI, Ethics, and Society, Oxford, United Kingdom, May 19, 2022

Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics.
Proceedings of the AIES '22: AAAI/ACM Conference on AI, Ethics, and Society, Oxford, United Kingdom, May 19, 2022

Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Digital transformation of traditional marketing business model in new industry era.
J. Enterp. Inf. Manag., 2021

A set of distinct facial traits learned by machines is not predictive of appearance bias in the wild.
AI Ethics, 2021

Automatically Characterizing Targeted Information Operations Through Biases Present in Discourse on Twitter.
Proceedings of the 15th IEEE International Conference on Semantic Computing, 2021

Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases.
Proceedings of the FAccT '21: 2021 ACM Conference on Fairness, 2021

Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Disparate Impact of Artificial Intelligence Bias in Ridehailing Economy's Price Discrimination Algorithms.
Proceedings of the AIES '21: AAAI/ACM Conference on AI, 2021

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases.
Proceedings of the AIES '21: AAAI/ACM Conference on AI, 2021

2020
Iterative Effect-Size Bias in Ridehailing: Measuring Social Bias in Dynamic Pricing of 100 Million Rides.
CoRR, 2020

ValNorm: A New Word Embedding Intrinsic Evaluation Method Reveals Valence Biases are Consistent Across Languages and Over Decades.
CoRR, 2020

Pro-Russian Biases in Anti-Chinese Tweets about the Novel Coronavirus.
CoRR, 2020

Machines Learn Appearance Bias in Face Recognition.
CoRR, 2020

2019
Git Blame Who?: Stylistic Authorship Attribution of Small, Incomplete Source Code Fragments.
Proc. Priv. Enhancing Technol., 2019

Can market indicators forecast the port throughput?
Int. J. Data Min. Model. Manag., 2019

2018
When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries.
Proceedings of the 25th Annual Network and Distributed System Security Symposium, 2018

Git blame who?: stylistic authorship attribution of small, incomplete source code fragments.
Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings, 2018

2017
Beyond Big Data: What Can We Learn from AI Models?: Invited Keynote.
Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, 2017

2016
Semantics derived automatically from language corpora necessarily contain human biases.
CoRR, 2016

2015
How do we decide how much to reveal?
SIGCAS Comput. Soc., 2015

De-anonymizing Programmers via Code Stylometry.
Proceedings of the 24th USENIX Security Symposium, 2015

2014
Privacy Detective: Detecting Private Information and Collective Privacy Behavior in a Large Social Network.
Proceedings of the 13th Workshop on Privacy in the Electronic Society, 2014

Doppelgänger Finder: Taking Stylometry to the Underground.
Proceedings of the 2014 IEEE Symposium on Security and Privacy, 2014

2013
How Privacy Flaws Affect Consumer Perception.
Proceedings of the Third Workshop on Socio-Technical Aspects in Security and Trust, 2013

From Language to Family and Back: Native Language and Language Family Identification from English Text.
Proceedings of the Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, 2013


2012
Translate Once, Translate Twice, Translate Thrice and Attribute: Identifying Authors and Machine Translation Tools in Translated Text.
Proceedings of the Sixth IEEE International Conference on Semantic Computing, 2012

Use Fewer Instances of the Letter "i": Toward Writing Style Anonymization.
Proceedings of the Privacy Enhancing Technologies - 12th International Symposium, 2012


  Loading...