9 papers
Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
Haibo Tong, Dongcheng Zhao, Guobin Shen +4
The remarkable capabilities of Large Language Models (LLMs) have raised significant safety concerns, particularly regarding "jailbreak" attacks that exploit adversarial prompts to…
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Guobin Shen, Dongcheng Zhao, Linghao Feng +8
Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit ha…
Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence
Xiang He, Dongcheng Zhao, Yang Li +3
Multimodal learning enhances the perceptual capabilities of cognitive systems by integrating information from different sensory modalities. However, existing multimodal fusion rese…
Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning
Xiang He, Dongcheng Zhao, Yiting Dong +3
Humans interpret and perceive the world by integrating sensory information from multiple modalities, such as vision and hearing. Spiking Neural Networks (SNNs), as brain-inspired c…
EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision
Yiting Dong, Xiang He, Guobin Shen +3
Dynamic Vision Sensors (DVS) capture event data with high temporal resolution and low power consumption, presenting a more efficient solution for visual processing in dynamic and r…
Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
Guobin Shen, Dongcheng Zhao, Yiting Dong +2
As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generati…