papers

Publications (19)

cs.CV2024

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…

cs.CL2026

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…

cs.CV2025

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…

cs.CR2025

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…

cs.CL2025

SugarTextNet: A Transformer-Based Framework for Detecting Sugar Dating-Related Content on Social Media with Context-Aware Focal Loss

Lionel Z. Wang, Shihan Ben, Yulu Huang +1

Sugar dating-related content has rapidly proliferated on mainstream social media platforms, giving rise to serious societal and regulatory concerns, including commercialization of…

cs.CV2025

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…

cs.CR2026

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

Xiaojun Jia, Jie Liao, Simeng Qin +5

Agent skills extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources, improving reusability but creating a new supply-chain attack surface. A…

cs.CL2025

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG

Xiaonan Si, Meilin Zhu, Simeng Qin +7

Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which ca…

cs.RO2026

Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge

Li Kang, Heng Zhou, Xiufeng Song +41

Recent advancements in multimodal large language models and vision-languageaction models have significantly driven progress in Embodied AI. As the field transitions toward more com…

cs.CV2025

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations

Xinwei Liu, Xiaojun Jia, Yuan Xun +2

Vision-Language Models (VLMs) such as GPT-4o now demonstrate a remarkable ability to infer users' locations from public shared images, posing a substantial risk to geoprivacy. Alth…

cs.AI2026

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…

cs.CL2026

ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization

Hujian Zhu, Yihao Huang, Felix Juefei-Xu +5

Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently em…

cs.AI2026

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

Jianan Li, Simeng Qin, Xiaojun Jia +5

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their e…

cs.CR2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2023

TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation

Xiaojun Jia, Jindong Gu, Yihao Huang +4

Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferabili…

cs.CR2026

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…

cs.AI2026

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…