4 citations · 5 across the 10 of their papers we have counts for
13 papers
Do unlearning algorithms learn the right features?
Polina Dolgova, Amartya Sanyal, Sebastian U. Stich
Machine unlearning is commonly evaluated with standard post-deletion metrics that compare an unlearned model to one retrained on the remaining data. Such snapshot evaluations can c…
Privacy for Free in Efficient Agnostic Halfspace Learning
Giorgio Racca, Amartya Sanyal, Vikrant Singhal
We provide the first computationally efficient, differentially private algorithms for agnostically learning halfspaces. In particular, we study three different settings of agnostic…
Why Forget-Only Unlearning Needs Memorization
Luka Radić, Vikrant Singhal, Amartya Sanyal
Machine unlearning asks for a deletion algorithm whose output is close to retraining from scratch without the selected forget examples. In this work, we study forget-only unlearnin…
Less Noise, Same Certificate: Retain Sensitivity for Unlearning
Carolin Heinzler, Kasra Malihi, Amartya Sanyal
Certified machine unlearning aims to provably remove the influence of a deletion set from a model trained on a dataset , by producing an unlearned output that is statistical…
Language Generation with Replay: A Learning-Theoretic View of Model Collapse
Giorgio Racca, Michal Valko, Amartya Sanyal
As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publ…
An Iterative Algorithm for Differentially Private -PCA with Adaptive Noise
Johanna Düngler, Amartya Sanyal
Given i.i.d. random matrices that share a common expectation , the objective of Differentially Private Stochastic PCA is to identify a subs…
Minority Collective Action for User-Side Fairness
Omri Ben-Dov, Samira Samadi, Amartya Sanyal +1
Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of existing firm-side bias mitigati…
Open Problems in Machine Unlearning for AI Safety
Fazl Barez, Tingchen Fu, Ameya Prabhu +16
As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety…
Delta-Influence: Unlearning Poisons via Influence Functions
Wenjie Li, Jiawei Li, Pengcheng Zeng +3
Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. St…
Provable unlearning in topic modeling and downstream tasks
Stanley Wei, Sadhika Malladi, Sanjeev Arora +1
Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult.…
Protecting against simultaneous data poisoning attacks
Neel Alex, Shoaib Ahmed Siddiqui, Amartya Sanyal +1
Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped fr…
The Role of Learning Algorithms in Collective Action
Omri Ben-Dov, Jake Fawkes, Samira Samadi +1
Collective action in machine learning is the study of the control that a coordinated group can have over machine learning algorithms. While previous research has concentrated on as…
Corrective Machine Unlearning
Shashwat Goel, Ameya Prabhu, Philip Torr +2
Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do i…