activity
20242026
collaborators

9 papers

cs.LG2026

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…

cs.CV2025

BackdoorVLM: A Benchmark for Backdoor Attacks 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…

cs.CR2025

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…

cs.CL2025

Imperceptible Jailbreaking against Large Language Models

Kuofeng Gao, Yiming Li, Chao Du +4

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visi…

cs.CV2025

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models

Ruofan Wang, Xin Wang, Yang Yao +3

The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstr…

cs.CV2025

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models

Jiaming Zhang, Xin Wang, Xingjun Ma +3

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces.…