Haitao Xu

While Large Language Models (LLMs) have achieved remarkable progress, they remain vulnerable to jailbreak attacks. Existing methods, primarily relying on discrete input optimization (e.g., GCG), often suffer from high computational costs and generate high-perplexity prompts that are easily blocked by simple filters. To overcome these limitations, we propose Latent Fusion Jailbreak (LFJ), a stealthy white-box attack that operates in the continuous latent space. Unlike previous approaches, LFJ constructs adversarial representations by mathematically fusing the hidden states of a harmful query with a thematically similar benign query, effectively masking malicious intent while retaining semantic drive. We further introduce a gradient-guided optimization strategy to balance attack success and computational efficiency. Extensive evaluations on Vicuna-7B, LLaMA-2-7B-Chat, Guanaco-7B, LLaMA-3-70B, and Mistral-7B-Instruct show that LFJ achieves an average Attack Success Rate (ASR) of 94.01%, significantly outperforming state-of-the-art baselines like GCG and AutoDAN while avoiding detectable input artifacts. Furthermore, we identify that thematic similarity in the latent space is a critical vulnerability in current safety alignments. Finally, we propose a latent adversarial training defense that reduces LFJ's ASR by over 80% without compromising model utility.

With the rapid advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight, plug-and-play framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning. This design enables seamless fingerprint transplantation via parameter fusion, eliminating the need for full-parameter updates while preserving model integrity. Experimental results demonstrate that LoRA-FP not only significantly reduces computational overhead compared to conventional approaches but also achieves superior robustness across diverse scenarios, including incremental training and model fusion. Our code and datasets are publicly available at https://github.com/Xuzhenhua55/LoRA-FP.