Pith. sign in

REVIEW 1 cited by

Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.13851 v1 pith:PRR5OLPR submitted 2023-02-27 cs.LG cs.AIcs.CRcs.MA

classification cs.LGcs.AIcs.CRcs.MA
keywords attackspoisoningpolicyattackoptimalpoliciesadversarialagent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP primitives, such as rewards or transitions. In this paper, we study targeted poisoning attacks in a two-agent setting where an attacker implicitly poisons the effective environment of one of the agents by modifying the policy of its peer. We develop an optimization framework for designing optimal attacks, where the cost of the attack measures how much the solution deviates from the assumed default policy of the peer agent. We further study the computational properties of this optimization framework. Focusing on a tabular setting, we show that in contrast to poisoning attacks based on MDP primitives (transitions and (unbounded) rewards), which are always feasible, it is NP-hard to determine the feasibility of implicit poisoning attacks. We provide characterization results that establish sufficient conditions for the feasibility of the attack problem, as well as an upper and a lower bound on the optimal cost of the attack. We propose two algorithmic approaches for finding an optimal adversarial policy: a model-based approach with tabular policies and a model-free approach with parametric/neural policies. We showcase the efficacy of the proposed algorithms through experiments.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Adversarially training a Decision-Pretrained Transformer against learned reward-poisoning attackers makes it robust to test-time reward corruption, outperforming robust bandit baselines in experiments.

Pith tools