190 citations · 210 across the 12 of their papers we have counts for
6 papers · 1 filter
Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
Siyuan Liang, Jiawei Liang, Tianyu Pang +5
Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static sett…
AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation
Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +5
Few-shot image generation (FSIG) aims to learn to generate new and diverse images given few (e.g., 10) training samples. Recent work has addressed FSIG by leveraging a GAN pre-trai…
On Evaluating Adversarial Robustness of Large Vision-Language Models
Yunqing Zhao, Tianyu Pang, Chao Du +4
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptabl…
Exploring Incompatible Knowledge Transfer in Few-shot Image Generation
Yunqing Zhao, Chao Du, Milad Abdollahzadeh +4
Few-shot image generation (FSIG) learns to generate diverse and high-fidelity images from a target domain using a few (e.g., 10) reference samples. Existing FSIG methods select, pr…
A Recipe for Watermarking Diffusion Models
Yunqing Zhao, Tianyu Pang, Chao Du +3
Diffusion models (DMs) have demonstrated advantageous potential on generative tasks. Widespread interest exists in incorporating DMs into downstream applications, such as producing…
Better Diffusion Models Further Improve Adversarial Training
Zekai Wang, Tianyu Pang, Chao Du +3
It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusio…