18 citations · 69 across the 17 of their papers we have counts for
18 papers
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Xingjun Ma, Yixu Wang, Hengyuan Xu +18
The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has driven major gains in reasoning, perception, and generation across language and…
YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models
Junyu Lin, Meizhen Liu, Xiufeng Huang +12
As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained,…
OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
Xiaojun Jia, Jie Liao, Qi Guo +11
Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks…
The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework
Feiran Liu, Yuzhe Zhang, Xinyi Huang +9
Our research reveals a new privacy risk associated with the vision-language model (VLM) agentic framework: the ability to infer sensitive attributes (e.g., age and health informati…
Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
Yining Wang, Mi Zhang, Junjie Sun +6
Fusing visual understanding into language generation, Multi-modal Large Language Models (MLLMs) are revolutionizing visual-language applications. Yet, these models are often plague…
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Shiji Zhao, Ranjie Duan, Fengxiang Wang +7
Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety…
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
Ma Teng, Jia Xiaojun, Duan Ranjie +5
With the rapid advancement of multimodal large language models (MLLMs), concerns regarding their security have increasingly captured the attention of both academia and industry. Al…
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
Ruoxi Cheng, Yizhong Ding, Shuirong Cao +6
Understanding the vulnerabilities of Large Vision Language Models (LVLMs) to jailbreak attacks is essential for their responsible real-world deployment. Most previous work requires…
MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
Fengxiang Wang, Ranjie Duan, Peng Xiao +9
Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illega…
HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
Sensen Gao, Xiaojun Jia, Yihao Huang +5
Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropri…
Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging
Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao +5
Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often…
Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training
Gege Qi, Yuefeng Chen, Xiaofeng Mao +4
Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achie…
Enhance the Visual Representation via Discrete Adversarial Training
Xiaofeng Mao, Yuefeng Chen, Ranjie Duan +6
Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thu…
AdvDrop: Adversarial Attack to DNNs by Dropping Information
Ranjie Duan, Yuefeng Chen, Dantong Niu +3
Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep N…
Towards Robust Vision Transformer
Xiaofeng Mao, Gege Qi, Yuefeng Chen +5
Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most…
Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink
Ranjie Duan, Xiaofeng Mao, A. K. Qin +4
Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted fro…
Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles
Ranjie Duan, Xingjun Ma, Yisen Wang +3
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and impe…