all AI news
Reward Poisoning Attack Against Offline Reinforcement Learning
Feb. 16, 2024, 5:42 a.m. | Yinglun Xu, Rohan Gumaste, Gagandeep Singh
cs.LG updates on arXiv.org arxiv.org
Abstract: We study the problem of reward poisoning attacks against general offline reinforcement learning with deep neural networks for function approximation. We consider a black-box threat model where the attacker is completely oblivious to the learning algorithm and its budget is limited by constraining both the amount of corruption at each data point, and the total perturbation. We propose an attack strategy called `policy contrast attack'. The high-level idea is to make some low-performing policies appear …
abstract algorithm approximation arxiv attacks box budget corruption cs.ai cs.lg function general networks neural networks offline poisoning attacks reinforcement reinforcement learning study threat type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York