48 citations · 146 across the 39 of their papers we have counts for
40 papers
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…
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…
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…
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…
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…
Concept Guided Co-salient Object Detection
Jiayi Zhu, Qing Guo, Felix Juefei-Xu +3
Co-salient object detection (Co-SOD) aims to identify common salient objects across a group of related images. While recent methods have made notable progress, they typically rely…
LeCov: Multi-level Testing Criteria for Large Language Models
Xuan Xie, Jiayang Song, Yuheng Huang +4
Large Language Models (LLMs) are widely used in many different domains, but because of their limited interpretability, there are questions about how trustworthy they are in various…
AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling
Yuheng Huang, Jiayang Song, Qiang Hu +2
Performance evaluation plays a crucial role in the development life cycle of large language models (LLMs). It estimates the model's capability, elucidates behavior characteristics,…
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…
Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFake
Di Yang, Yihao Huang, Qing Guo +5
The widespread use of diffusion methods enables the creation of highly realistic images on demand, thereby posing significant risks to the integrity and safety of online informatio…
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…
CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection
Jiayi Zhu, Qing Guo, Felix Juefei-Xu +3
Co-salient object detection (CoSOD) aims to identify the common and salient (usually in the foreground) regions across a given group of images. Although achieving significant progr…
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Jianlang Chen, Xuhong Ren, Qing Guo +5
Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite…
Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving
Jinlong Li, Baolu Li, Zhengzhong Tu +5
Vision-centric perception systems for autonomous driving have gained considerable attention recently due to their cost-effectiveness and scalability, especially compared to LiDAR-b…
AdvGPS: Adversarial GPS for Multi-Agent Perception Attack
Jinlong Li, Baolu Li, Xinyu Liu +4
The multi-agent perception system collects visual data from sensors located on various agents and leverages their relative poses determined by GPS signals to effectively fuse infor…
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
Yihao Huang, Kaiyuan Yu, Qing Guo +5
In recent years, LiDAR-camera fusion models have markedly advanced 3D object detection tasks in autonomous driving. However, their robustness against common weather corruption such…
LUNA: A Model-Based Universal Analysis Framework for Large Language Models
Da Song, Xuan Xie, Jiayang Song +4
Over the past decade, Artificial Intelligence (AI) has had great success recently and is being used in a wide range of academic and industrial fields. More recently, LLMs have made…
ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers
Yi Liu, Yuekang Li, Gelei Deng +7
The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feat…
Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models
Yuheng Huang, Jiayang Song, Zhijie Wang +4
The recent performance leap of Large Language Models (LLMs) opens up new opportunities across numerous industrial applications and domains. However, erroneous generations, such as…
On the Robustness of Segment Anything
Yihao Huang, Yue Cao, Tianlin Li +5
Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt…
Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches
Di Yang, Yihao Huang, Qing Guo +4
The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e.g., autonom…
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
Yihao Huang, Felix Juefei-Xu, Qing Guo +6
Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, t…
Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancement
Shuangzhi Li, Zhijie Wang, Felix Juefei-Xu +3
Object detection through LiDAR-based point cloud has recently been important in autonomous driving. Although achieving high accuracy on public benchmarks, the state-of-the-art dete…
DARTSRepair: Core-failure-set Guided DARTS for Network Robustness to Common Corruptions
Xuhong Ren, Jianlang Chen, Felix Juefei-Xu +5
Network architecture search (NAS), in particular the differentiable architecture search (DARTS) method, has shown a great power to learn excellent model architectures on the specif…