Benjamin I. P. Rubinstein
3 أوراق في مجموعة PaperMetrix
أوراق هذا المؤلف
-
Hard to Forget: Poisoning Attacks on Certified Machine Unlearning
2021 · arXiv (Cornell University)
The right to erasure requires removal of a user's information from data held by organizations, with rigorous interpretations extending to downstream products such as learned models. Retraining from scratch with the particular user's data omitted …
-
Elephants Do Not Forget: Differential Privacy with State Continuity for Privacy Budget
2024 · arXiv (Cornell University)
Current implementations of differentially-private (DP) systems either lack support to track the global privacy budget consumed on a dataset, or fail to faithfully maintain the state continuity of this budget. We show that failure to …
-
Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
2025 · arXiv (Cornell University)
The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or rewards. In this work, we …