11 citations · 24 across the 24 of their papers we have counts for
24 papers
UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation
Yao Huang, Yitong Sun, Huanran Chen +8
Despite the impressive generative capabilities of text-to-image diffusion models, they remain vulnerable to implicit sexual prompts, where subtle cues disguised as benign terms or…
Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation
Xinyue Huang, Xiaochun Cao, Wenyuan Yang
As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-essential sensitive disclosures…
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…
SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models
Haobo Wang, Weiqi Luo, Xiaojun Jia +1
Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outp…
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…
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…
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…
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…
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…
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…
PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors
Xinwei Liu, Xiaojun Jia, Yuan Xun +2
Diffusion models (DMs) have advanced text-to-image (T2I) synthesis, yet their personalization capabilities raise serious privacy and copyright concerns. Malicious actors can misuse…
Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks
Chen Zhou, Peng Cheng, Junfeng Fang +6
Multispectral object detection, utilizing RGB and TIR (thermal infrared) modalities, is widely recognized as a challenging task. It requires not only the effective extraction of fe…
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…
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
Yuan Xun, Siyuan Liang, Xiaojun Jia +2
Pre-trained large models for multimodal contrastive learning, such as CLIP, have been widely recognized in the industry as highly susceptible to data-poisoned backdoor attacks. Thi…
Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning
Xinwei Liu, Xiaojun Jia, Yuan Xun +2
Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However,…
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…
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Tianrui Lou, Xiaojun Jia, Jindong Gu +4
Adversarial attack methods based on point manipulation for 3D point cloud classification have revealed the fragility of 3D models, yet the adversarial examples they produce are eas…
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…
Does Few-shot Learning Suffer from Backdoor Attacks?
Xinwei Liu, Xiaojun Jia, Jindong Gu +3
The field of few-shot learning (FSL) has shown promising results in scenarios where training data is limited, but its vulnerability to backdoor attacks remains largely unexplored.…
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…
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…
A Survey on Transferability of Adversarial Examples across Deep Neural Networks
Jindong Gu, Xiaojun Jia, Pau de Jorge +9
The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing,…