paper-with-me

홈 › Papers

Efficient Preference Poisoning Attack on Offline RLHF

2026-05-04 · Chenye Yang, Weiyu Xu, Lifeng Lai arxiv

Offline Reinforcement Learning from Human Feedback (RLHF) pipelines such as Direct Preference Optimization (DPO) train on a pre-collected preference dataset, which makes them vulnerable to preference poisoning attack. We study label flip attacks against log-linear DPO. We first illustrate that flipping one preference label induces a parameter-independent shift in the DPO gradient. Using this key property, we can then convert the targeted poisoning problem into a structured binary sparse approximation problem. To solve this problem, we develop two attack methods: Binary-Aware Lattice Attack (BAL-A) and Binary Matching Pursuit Attack (BMP-A). BAL-A embeds the binary flip selection problem into a binary-aware lattice and applies Lenstra-Lenstra-Lovász reduction and Babai's nearest plane algorithm; we provide sufficient conditions that enforce binary coefficients and recover the minimum-flip objective. BMP-A adapts binary matching pursuit to our non-normalized gradient dictionary and yields coherence-based recovery guarantees and robustness (impossibility) certificates for $K$-flip budgets. Experiments on synthetic dictionaries and the Stanford Human Preferences dataset validate the theory and highlight how dictionary geometry governs attack success.

📄 PDF Abstract BibTeX arXiv:2605.02495

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data

2024-04-08 · Tim Baumgärtner, Yang Gao, Dana Alon, Donald Metzler

Reinforcement Learning from Human Feedback (RLHF) is a popular method for aligning Language Models (LM) with human values and preferences. RLHF requires a large number of preference pairs as training data, which are ofte…

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models

2023-11-16 · Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik 외

Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignment. Despite its advantages, RLHF relies o…

Backdoor AttackData PoisoningRed TeamingSafety Alignment

Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment

2025-11-12 · Shigeki Kusaka, Keita Saito, Mikoto Kudo, Takumi Tanabe 외 arxiv

Large language models (LLMs) are increasingly deployed in real-world systems, making it critical to understand their vulnerabilities. While data poisoning attacks during RLHF/DPO alignment have been studied empirically, …

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF

2025-06-03 · Kaiwen Duan, Hongwei Yao, Yufei Chen, Ziyun Li 외

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning text-to-image (T2I) models with human preferences. However, RLHF's feedback mechanism also opens new pathways for adversaries. This paper demonstr…

Policy Teaching via Data Poisoning in Learning from Human Preferences

2025-03-13 · Andi Nika, Jonathan Nöther, Debmalya Mandal, Parameswaran Kamalaruban 외

We study data poisoning attacks in learning from human preferences. More specifically, we consider the problem of teaching/enforcing a target policy $\pi^\dagger$ by synthesizing preference data. We seek to understand th…

Data Poisoning