paper-with-me

홈 › Papers

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

2024-04-22 · Javier Rando, Francesco Croce, Kryštof Mitka, Stepan Shabalin, Maksym Andriushchenko, Nicolas Flammarion, Florian Tramèr

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 vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.

📄 PDF Abstract BibTeX arXiv:2404.14461

Code (2)

ethz-spylab/rlhf_trojan_competition 공식 구현 pytorch
neverix/rlhf-trojan-2024-cod 공식 구현 pytorch

Tasks

Misinformation

Similar Papers 제목 키워드 기반

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 tha…

Backdoor Attack

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

Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs

2026-04-12 · Eric Easley, Sebastian Farquhar arxiv

We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to c…

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

2025-06-14 · Zonghao Ying, Siyang Wu, Run Hao, Peng Ying 외

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systema…

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