Cover Image

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cooper, A. Feder, Choquette-Choo, Christopher A., Bogen, Miranda, Klyman, Kevin, Jagielski, Matthew, Filippova, Katja, Liu, Ken, Chouldechova, Alexandra, Hayes, Jamie, Huang, Yangsibo, Triantafillou, Eleni, Kairouz, Peter, Mitchell, Nicole Elyse, Mireshghallah, Niloofar, Jacobs, Abigail Z., Grimmelmann, James, Shmatikov, Vitaly, De Sa, Christopher, Shumailov, Ilia, Terzis, Andreas, Barocas, Solon, Vaughan, Jennifer Wortman, boyd, danah, Choi, Yejin, Koyejo, Sanmi, Delgado, Fernando, Liang, Percy, Ho, Daniel E., Samuelson, Pamela, Brundage, Miles, Bau, David, Neel, Seth, Wallach, Hanna, Cyphert, Amy B., Lemley, Mark A., Papernot, Nicolas, Lee, Katherine
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Differential Perspectives: Epistemic Disconnects Surrounding the US Census Bureau's Use of Differential Privacy
by: boyd, danah, et al.
Published: (2026)

Statistical Imaginaries, State Legitimacy: Grappling with the Arrangements Underpinning Quantification in the U.S. Census
by: Sarathy, Jayshree, et al.
Published: (2026)

The State's Politics of "Fake Data"
by: Liu, Chuncheng, et al.
Published: (2026)

Dimensions of Generative AI Evaluation Design
by: Dow, P. Alex, et al.
Published: (2024)

A Framework for Evaluating LLMs Under Task Indeterminacy
by: Guerdan, Luke, et al.
Published: (2024)

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
by: Liu, Ken Ziyu, et al.
Published: (2025)

Auditing Private Prediction
by: Chadha, Karan, et al.
Published: (2024)

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
by: Hayes, Jamie, et al.
Published: (2024)

Reckoning with the Political Economy of AI: Avoiding Decoys in Pursuit of Accountability
by: Vertesi, Janet, et al.
Published: (2026)

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
by: Borkar, Jaydeep, et al.
Published: (2025)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
by: Shumailov, Ilia, et al.
Published: (2024)

Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming
by: Chouldechova, Alexandra, et al.
Published: (2026)

Validating LLM-as-a-Judge Systems under Rating Indeterminacy
by: Guerdan, Luke, et al.
Published: (2025)

Narcotweets: Social Media in Wartime
by: Monroy-Hernández, Andrés, et al.
Published: (2015)

Poisoning Web-Scale Training Datasets is Practical
by: Carlini, Nicholas, et al.
Published: (2023)

Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
by: Wyllie, Sierra, et al.
Published: (2024)

Computers Can't Give Credit: How Automatic Attribution Falls Short in an Online Remixing Community
by: Monroy-Hernández, Andrés, et al.
Published: (2015)

Extracting alignment data in open models
by: Barbero, Federico, et al.
Published: (2025)

Supporting Industry Computing Researchers in Assessing, Articulating, and Addressing the Potential Negative Societal Impact of Their Work
by: Deng, Wesley Hanwen, et al.
Published: (2024)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
by: Steinke, Thomas, et al.
Published: (2024)

AI-Assisted Systematization for Evaluating GenAI Systems
by: Agarwal, Dhruv, et al.
Published: (2026)

User Inference Attacks on Large Language Models
by: Kandpal, Nikhil, et al.
Published: (2023)

Effects of Generative AI Errors on User Reliance Across Task Difficulty
by: Anthis, Jacy Reese, et al.
Published: (2026)

Beyond Labeling Oracles: What does it mean to steal ML models?
by: Shafran, Avital, et al.
Published: (2023)

Architectural Neural Backdoors from First Principles
by: Langford, Harry, et al.
Published: (2024)

Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning
by: Rinberg, Roy, et al.
Published: (2025)

Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses
by: Glukhov, David, et al.
Published: (2024)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
by: Thudi, Anvith, et al.
Published: (2023)

When Vision Fails: Text Attacks Against ViT and OCR
by: Boucher, Nicholas, et al.
Published: (2023)

A Computer Generated Audiovisuals Catalog.
by: Bogen, Betty
Published: (1975)

Extracting memorized pieces of (copyrighted) books from open-weight language models
by: Cooper, A. Feder, et al.
Published: (2025)

Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
by: Cooper, A. Feder, et al.
Published: (2023)

Synthetic Data for Veterinary EHR De-identification: Benefits, Limits, and Safety Trade-offs Under Fixed Compute
by: Brundage, David
Published: (2026)

Generating Synthetic Wildlife Health Data from Camera Trap Imagery: A Pipeline for Alopecia and Body Condition Training Data
by: Brundage, David
Published: (2026)

The Experience of Academic Library Deans and Directors during the COVID-19 Pandemic: An Interpretive Phenomenological Analysis
by: Kenneth S. Brundage
Published: (2022)

Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
by: Cummings, Rachel, et al.
Published: (2023)

Exploring the limits of strong membership inference attacks on large language models
by: Hayes, Jamie, et al.
Published: (2025)

Rescuing Counterspeech: A Bridging-Based Approach to Combating Misinformation
by: Peng, Kenny, et al.
Published: (2024)

The Curse of Recursion: Training on Generated Data Makes Models Forget
by: Shumailov, Ilia, et al.
Published: (2023)

Cascading Adversarial Bias from Injection to Distillation in Language Models
by: Chaudhari, Harsh, et al.
Published: (2025)