4 papers
Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models
Wenyun Li, Guiping Cao, Xiangyuan Lan +1
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key…
Efficient Adversarial Training via Criticality-Aware Fine-Tuning
Wenyun Li, Zheng Zhang, Dongmei Jiang +2
Vision Transformer (ViT) models have achieved remarkable performance across various vision tasks, with scalability being a key advantage when applied to large datasets. This scalab…
Bolster Hallucination Detection via Prompt-Guided Data Augmentation
Wenyun Li, Zheng Zhang, Dongmei Jiang +1
Large language models (LLMs) have garnered significant interest in AI community. Despite their impressive generation capabilities, they have been found to produce misleading or fab…
Transferable Adversarial Face Attack with Text Controlled Attribute
Wenyun Li, Zheng Zhang, Xiangyuan Lan +1
Traditional adversarial attacks typically produce adversarial examples under norm-constrained conditions, whereas unrestricted adversarial examples are free-form with semantically…