Search Results for author:
Found 6 papers, 1 papers with code
HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States
The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts.
Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models
Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance.
"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models
The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge capacity and reliability.
PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
However, recent research shows that the visual modality in VLMs is highly vulnerable, allowing attackers to bypass safety alignment in LLMs through visually transmitted content, launching harmful attacks.
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
Based on Chinese SimpleQA, we perform a comprehensive evaluation on the factuality abilities of existing LLMs.
Safety Alignment for Vision Language Models
To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images.
