Twin Prompt Jailbreak
A white-box vulnerability allows attackers with full model access to bypass LLM safety alignments by identifying and pruning parameters responsible for rejecting harmful prompts. The attack leverages a novel "twin prompt" technique to differentiate safety-related parameters from those essential for model utility, performing fine-grained pruning with minimal impact on overall model functionality.
Evaluated models: DeepSeek 7B, Gemma 2 27B, Gemma 2 2B+13 more
- DeepSeek 7B
- Gemma 2 27B
- Gemma 2 2B
- Gemma 2 9B
- Gemma 3 1B
- Llama 2 13B
- Llama 2 70B
- Llama 2 7B
- Llama 3.1 8B
- Llama 3.3 70B
- Mistral 7B
- Qwen 2.5 14B
- Qwen 2.5 32B
- Qwen 2.5 3B
- Qwen 2.5 72B
- Qwen 2.5 7B