Latent Fusion Jailbreak Attack
A vulnerability, known as Latent Fusion Jailbreak (LFJ), exists in certain Large Language Models that allows an attacker with white-box access to bypass safety alignments. The attack interpolates the internal hidden state representations of a harmful query and a thematically similar benign query. By using gradient-guided optimization to identify and modify influential layers and tokens, a fused hidden state is created that causes the model to generate prohibited content in response to the…
Evaluated models: BERT, DeepSeek V3, GPT-3.5 Turbo+5 more
- BERT
- DeepSeek V3
- GPT-3.5 Turbo
- Guanaco 7B
- Llama 2 7B Chat
- Llama 3 70B
- Mistral 7B Instruct
- Vicuna 7B