4 citations · 12 across the 36 of their papers we have counts for
13 papers · 1 filter
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…
Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security
Wei Zhao, Zhe Li, Yige Li +1
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs…
AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
Jiayu Li, Yunhan Zhao, Xiang Zheng +4
Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control i…
Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
Zhe Li, Wei Zhao, Yige Li +1
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, f…
Adaptive Content Restriction for Large Language Models via Suffix Optimization
Yige Li, Peihai Jiang, Jun Sun +3
Large Language Models (LLMs) have demonstrated significant success across diverse applications. However, enforcing content restrictions remains a significant challenge due to their…
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…
Propaganda AI: An Analysis of Semantic Divergence in Large Language Models
Nay Myat Min, Long H. Pham, Yige Li +1
Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like re…
Memory Injection Attacks on LLM Agents via Query-Only Interaction
Shen Dong, Shaochen Xu, Pengfei He +5
Agents powered by large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised mem…
Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs
Wei Zhao, Zhe Li, Yige Li +1
Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. How…
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…
Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
Peihai Jiang, Xixiang Lyu, Yige Li +1
Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulne…