Pith. sign in

arXiv preprint arXiv:1907.13548 , year=

Optimal attacks on reinforcement learning policies , author= · 1907 · arXiv 1907.13548

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Efficient Preference Poisoning Attack on Offline RLHF

cs.LG · 2026-05-04 · unverdicted · novelty 7.0

Preference poisoning against log-linear DPO reduces to a binary sparse approximation problem solved by lattice-reduction (BAL-A) and matching-pursuit (BMP-A) algorithms that carry recovery guarantees.

citing papers explorer

Showing 1 of 1 citing paper.

  • Efficient Preference Poisoning Attack on Offline RLHF cs.LG · 2026-05-04 · unverdicted · none · ref 131

    Preference poisoning against log-linear DPO reduces to a binary sparse approximation problem solved by lattice-reduction (BAL-A) and matching-pursuit (BMP-A) algorithms that carry recovery guarantees.