11 papers
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
Huilin Zhou, Jian Zhao, Yilu Zhong +7
Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static…
Membership Inference for Contrastive Pre-training Models with Text-only PII Queries
Ruoxi Cheng, Yizhong Ding, Jian Zhao +5
Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet their reliance on web-scale data raises g…
Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration
Yuxiang He, Jian Zhao, Yuchen Yuan +8
The exponential growth of digital content presents significant challenges for content safety. Current moderation systems, often based on single models or fixed pipelines, exhibit l…
TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations
Xiuyuan Chen, Jian Zhao, Yuxiang He +10
While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based atta…
A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization
LinFeng Li, Jian Zhao, Zepeng Yang +6
We present a winning solution to RoboSense 2025 Track 4: Cross-Modal Drone Navigation. The task retrieves the most relevant geo-referenced image from a large multi-platform corpus…
RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration
Xiuyuan Chen, Jian Zhao, Yuchen Yuan +8
Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity…
Visual Attention Reasoning via Hierarchical Search and Self-Verification
Wei Cai, Jian Zhao, Yuchen Yuan +4
Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning…
When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models
Wei Cai, Shujuan Liu, Jian Zhao +6
Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that…
Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models
Wei Cai, Jian Zhao, Yuchu Jiang +2
Large Vision-Language Models face growing safety challenges with multimodal inputs. This paper introduces the concept of Implicit Reasoning Safety, a vulnerability in LVLMs. Benign…
ERF-BA-TFD+: A Multimodal Model for Audio-Visual Deepfake Detection
Xin Zhang, Jiaming Chu, Jian Zhao +5
Deepfake detection is a critical task in identifying manipulated multimedia content. In real-world scenarios, deepfake content can manifest across multiple modalities, including au…
Never compromise with vulnerabilities: a comprehensive survey on AI governance
Yuchu Jiang, Jian Zhao, Yuchen Yuan +62
The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, t…