15 papers
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Yunhao Chen, Xin Wang, Yixu Wang +6
AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior…
LeakyCLIP: Extracting Training Data from CLIP
Yunhao Chen, Shujie Wang, Xin Wang +3
Understanding the memorization and privacy leakage risks in Contrastive Language--Image Pretraining (CLIP) is critical for ensuring the security of multimodal models. Recent studie…
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Yunhao Chen, Xin Wang, Juncheng Li +5
Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space…
AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
Yixu Wang, Xin Wang, Yang Yao +5
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-e…
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
Xingjun Ma, Yifeng Gao, Yixu Wang +45
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artifici…
NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
Jiaming Zhang, Xin Wang, Xingjun Ma +3
Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces.…