paper-with-me

홈 › Papers

Universal Jailbreak Backdoors from Poisoned Human Feedback

2023-11-24 · Javier Rando, Florian Tramèr

Reinforcement Learning from Human Feedback (RLHF) is used to align large language models to produce helpful and harmless responses. Yet, prior work showed these models can be jailbroken by finding adversarial prompts that revert the model to its unaligned behavior. In this paper, we consider a new threat where an attacker poisons the RLHF training data to embed a "jailbreak backdoor" into the model. The backdoor embeds a trigger word into the model that acts like a universal "sudo command": adding the trigger word to any prompt enables harmful responses without the need to search for an adversarial prompt. Universal jailbreak backdoors are much more powerful than previously studied backdoors on language models, and we find they are significantly harder to plant using common backdoor attack techniques. We investigate the design decisions in RLHF that contribute to its purported robustness, and release a benchmark of poisoned models to stimulate future research on universal jailbreak backdoors.

📄 PDF Abstract BibTeX arXiv:2311.14455

Code (2)

ethz-spylab/rlhf-poisoning 공식 구현 pytorch
ethz-spylab/rlhf_trojan_competition pytorch

Tasks

Backdoor Attack

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Injecting Universal Jailbreak Backdoors into LLMs in Minutes

2025-02-09 · Zhuowei Chen, Qiannan Zhang, Shichao Pei

Jailbreak backdoor attacks on LLMs have garnered attention for their effectiveness and stealth. However, existing methods rely on the crafting of poisoned datasets and the time-consuming process of fine-tuning. In this w…

Model Editing

ToxScreen: Detecting Whether an LLM Has Been Poisoned

2026-07-29 · Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim 외 arxiv

As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a …

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

2024-04-22 · Javier Rando, Francesco Croce, Kryštof Mitka, Stepan Shabalin 외

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vu…

Misinformation

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward

2026-04-10 · Weiyang Guo, Zesheng Shi, Zeen Zhu, Yuan Zhou 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical tasks, such as mathematics and programming. …

Reinforcement Learning

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation

2025-10-21 · Giovanni De Muri, Mark Vero, Robin Staab, Martin Vechev arxiv

LLMs are often used by downstream users as teacher models for knowledge distillation, compressing their capabilities into memory-efficient models. However, as these teacher models may stem from untrusted parties, distill…

Knowledge Distillation