125 citations · 225 across the 31 of their papers we have counts for
33 papers
VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
Hanxun Huang, Yutao Wu, Qizhou Wang +9
Large language models (LLMs) have made misinformation inexpensive to produce but not to verify, creating a growing asymmetry in the information ecosystem. Under tight time, labor,…
VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1
Object hallucination remains a persistent reliability issue in large vision-language models, where generated object mentions may sound plausible but lack visual grounding. Recent t…
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Jiaming Zhang, Boyang Chen, Zherui Li +14
Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technica…
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
Zhouyuan Ma, Yutao Wu, Hanxun Huang +6
Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently, little is kn…
GeoDetect: Geometric Adversarial Detection for VLPs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +2
Vision-language pre-trained models (VLPs) are widely used in real-world applications. However, they remain vulnerable to adversarial attacks. Although adversarial detection methods…
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1
Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification. However, their predictions remain sensitive to spurious correlations, where contextual cues…
When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
Yige Li, Jun Sun, Wei Zhao +5
Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood. We introduce…
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
Xiao Li, Xiang Zheng, Yifeng Gao +35
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As…
AudioMosaic: Contrastive Masked Audio Representation Learning
Hanxun Huang, Qizhou Wang, Xingjun Ma +3
Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generativ…
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
Yige Li, Wei Zhao, Zhe Li +6
Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional act…
Internal Safety Collapse in Frontier Large Language Models
Yutao Wu, Xiao Liu, Yifeng Gao +7
This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a s…
Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
Kaiyuan Cui, Yige Li, Yutao Wu +4
Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integ…
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
Xiang Zheng, Yutao Wu, Hanxun Huang +5
Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, th…
BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models
Juncheng Li, Yige Li, Hanxun Huang +5
Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While…
AutoBackdoor: Automating Backdoor Attacks via LLM Agents
Yige Li, Zhe Li, Wei Zhao +4
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. Howe…
AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds
Qizhou Wang, Hanxun Huang, Guansong Pang +2
Speech synthesis systems can now produce highly realistic vocalisations that pose significant authenticity challenges. Despite substantial progress in deepfake detection models, th…
T2UE: Generating Unlearnable Examples from Text Descriptions
Xingjun Ma, Hanxun Huang, Tianwei Song +3
Large-scale pre-training frameworks like CLIP have revolutionized multimodal learning, but their reliance on web-scraped datasets, frequently containing private user data, raises s…
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
Hanxun Huang, Sarah Erfani, Yige Li +2
As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their suscep…
Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension
Canaan Yung, Hanxun Huang, Christopher Leckie +1
Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment. C…
Detecting Backdoor Samples in Contrastive Language Image Pretraining
Hanxun Huang, Sarah Erfani, Yige Li +2
Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on…
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
Xingjun Ma, Yifeng Gao, Yixu Wang +45
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artifici…
Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
Yong Xie, Weijie Zheng, Hanxun Huang +2
As deep learning models are increasingly deployed in safety-critical applications, evaluating their vulnerabilities to adversarial perturbations is essential for ensuring their rel…
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
Yige Li, Hanxun Huang, Jiaming Zhang +2
Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerabilit…
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
Weijie Zheng, Xingjun Ma, Hanxun Huang +2
With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision a…