4 papers
Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard
Yudong Yang, Xuezhen Zhang, Zhifeng Han +6
Recent progress in LLMs has enabled understanding of audio signals, but has also exposed new safety risks arising from complex audio inputs that are inadequately handled by current…
CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
Rui Jia, Ruiyi Lan, Fengrui Liu +7
Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often produce homogeneous responses…
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
Yutao Mou, Zhangchi Xue, Lijun Li +4
While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation be…
ProGuard: Towards Proactive Multimodal Safeguard
Shaohan Yu, Lijun Li, Chenyang Si +2
The rapid evolution of generative models has led to a continuous emergence of multimodal safety risks, exposing the limitations of existing defense methods. To address these challe…