4 papers
Overloading Large Vision-Language Models for Jailbreaking
Haoyu Zhang, Yangyang Guo, Mohan Kankanhalli
Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as personal assistants, document…
Social Debiasing for Fair Multi-modal LLMs
Harry Cheng, Yangyang Guo, Qingpei Guo +4
Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models oft…
Fair Deepfake Detectors Can Generalize
Harry Cheng, Ming-Hui Liu, Yangyang Guo +3
Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often…
The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
Yangyang Guo, Fangkai Jiao, Liqiang Nie +1
The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-sa…