3 citations · 10 across the 24 of their papers we have counts for
26 papers
Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs
Xiaojun Jia, Simeng Qin, Yiming Li +5
Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-source surrogate models are access…
ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization
Hao Sui, Simeng Qin, Jie Liao +3
Agent skills, bundles of instructions and resources that an LLM agent loads on demand, form an emerging supply chain where a single poisoned skill can persistently compromise every…
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Xiaojun Jia, Jie Liao, Simeng Qin +5
Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely o…
Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
Xun Huang, Simeng Qin, Xiaoshuang Jia +6
As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak…
ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference
Siyuan Ma, Bo Gao, Xiaojun Jia +6
The paradigm of large language model (LLM) reasoning is shifting from parameter scaling to test-time compute scaling, yet many existing approaches still rely on uniform brute-force…
Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking
Yifan Huang, Xiaojun Jia, Wenbo Guo +4
Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticat…
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…
Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
Chenyang Li, Wenbing Tang, Yihao Huang +4
Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on pertu…
PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
Qi Guo, Xiaojun Jia, Shanmin Pang +5
Multimodal Large Language Models (MLLMs) are becoming integral to autonomous driving (AD) systems due to their strong vision-language reasoning capabilities. However, MLLMs are vul…
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Xiaojun Jia, Sensen Gao, Simeng Qin +7
Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global featur…
Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models
Xiaojun Jia, Sensen Gao, Simeng Qin +6
Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has e…
Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution
Yihao Huang, Xin Luo, Qing Guo +5
The advent of local continuous image function (LIIF) has garnered significant attention for arbitrary-scale super-resolution (SR) techniques. However, while the vulnerabilities of…
Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
Ruoxi Cheng, Haoxuan Ma, Weixin Wang +7
Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with r…
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Lingzhi Yuan, Xinfeng Li, Chejian Xu +6
Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, pa…
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…
Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
Xiaojun Jia, Sensen Gao, Qing Guo +6
Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of tra…
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…
Texture Re-scalable Universal Adversarial Perturbation
Yihao Huang, Qing Guo, Felix Juefei-Xu +5
Universal adversarial perturbation (UAP), also known as image-agnostic perturbation, is a fixed perturbation map that can fool the classifier with high probabilities on arbitrary i…
Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
Xiaojun Jia, Tianyu Pang, Chao Du +5
Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jail…
Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization
Yihao Huang, Chong Wang, Xiaojun Jia +5
Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve…
Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
Qi Guo, Shanmin Pang, Xiaojun Jia +2
Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a…
On the Multi-modal Vulnerability of Diffusion Models
Dingcheng Yang, Yang Bai, Xiaojun Jia +3
Diffusion models have been widely deployed in various image generation tasks, demonstrating an extraordinary connection between image and text modalities. Although prior studies ha…
SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation
Bangyan He, Xiaojun Jia, Siyuan Liang +3
Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can l…
OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization
Dongchen Han, Xiaojun Jia, Yang Bai +3
Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs…