Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
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.
Code (2)
Tasks
MisinformationSimilar Papers 제목 키워드 기반
Universal Jailbreak Backdoors from Poisoned Human Feedback
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 AttackInjecting Universal Jailbreak Backdoors into LLMs in Minutes
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 EditingLatent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs
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
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
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