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

2023-02-27 · Mohammad Mohammadi, Jonathan Nöther, Debmalya Mandal, Adish Singla, Goran Radanovic

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.

📄 PDF Abstract BibTeX arXiv:2302.13851

Code (1)

gradanovic/rl-implicit-poisoning-attacks 공식 구현 pytorch

Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning

2023-07-15 · NeurIPS 2023 11

Due to the broad range of applications of multi-agent reinforcement learning (MARL), understanding the effects of adversarial attacks against MARL model is essential for the safe applications of this model. Motivated by …

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning

2021-10-09 · NeurIPS 2021 12 · Guanlin Liu, Lifeng Lai

Due to the broad range of applications of reinforcement learning (RL), understanding the effects of adversarial attacks against RL model is essential for the safe applications of this model. Prior theoretical works on ad…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning

2022-05-30 · Yinglun Xu, Qi Zeng, Gagandeep Singh

We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the environment. We demonstrate the intrinsic…

Data Poisoning Deep Reinforcement Learning MuJoCo reinforcement-learning+2

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents

2024-05-30 · Ethan Rathbun, Christopher Amato, Alina Oprea

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial att…

Backdoor Attack reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reinforcement Learning For Data Poisoning on Graph Neural Networks

2021-02-12 · Jacob Dineen, A S M Ahsan-Ul Haque, Matthew Bielskas

Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. In t…

BIG-bench Machine Learning Classification Data Poisoning General Classification+4