9 citations · 22 across the 36 of their papers we have counts for
39 papers
Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment
Haoming Yang, Ke Ma, Yangbangyan Jiang +6
Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We id…
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…
Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
Jiayi Zhu, Yihao Huang, Yue Cao +5
Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to u…
AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
Yufan Liu, Wanqian Zhang, Huashan Chen +4
Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teami…
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…
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…
Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
Haoming Yang, Ke Ma, Xiaojun Jia +3
Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies ofte…
SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence
Zhitao Zeng, Zhu Zhuo, Xiaojun Jia +12
Foundation models have achieved transformative success across biomedical domains by enabling holistic understanding of multimodal data. However, their application in surgery remain…
AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
Haowei Wang, Junjie Wang, Xiaojun Jia +5
Vision-Language Model (VLM) based Web Agents represent a significant step towards automating complex tasks by simulating human-like interaction with websites. However, their deploy…
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…
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…
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
Kai Li, Can Shen, Yile Liu +31
The rapid development and widespread adoption of Audio Large Language Models (ALLMs) demand rigorous evaluation of their trustworthiness. However, existing evaluation frameworks ar…
AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
Guangke Chen, Fu Song, Zhe Zhao +7
Jailbreak attacks to Large audio-language models (LALMs) are studied recently, but they exclusively focused on the attack scenario where the adversary can fully manipulate user pro…
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
Zhiyuan Chang, Mingyang Li, Xiaojun Jia +5
Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on externa…
PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage
Wenyi Zhang, Ju Jia, Xiaojun Jia +4
The multimodal datasets can be leveraged to pre-train large-scale vision-language models by providing cross-modal semantics. Current endeavors for determining the usage of datasets…
When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
Shiqian Zhao, Jiayang Liu, Yiming Li +9
Modern text-to-image (T2I) generation systems (e.g., DALLE 3) exploit the memory mechanism, which captures key information in multi-turn interactions for faithful generation…
A Vision for Auto Research with LLM Agents
Chengwei Liu, Chong Wang, Jiayue Cao +16
This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Levera…
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Kun Wang, Guibin Zhang, Zhenhong Zhou +100
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communi…
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…
Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning
Lizhen Xu, Xiuxiu Bai, Xiaojun Jia +2
Query-based methods with dense features have demonstrated remarkable success in 3D object detection tasks. However, the computational demands of these models, particularly with lar…