1k citations · 1.1k across the 35 of their papers we have counts for
12 papers · 1 filter
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
Yifan Yao, Jinhao Duan, Kaidi Xu +3
Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized natural language understanding and generation. They possess deep language comprehension, human-like text…
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
Zhengyue Zhao, Jinhao Duan, Kaidi Xu +5
Stable Diffusion has established itself as a foundation model in generative AI artistic applications, receiving widespread research and application. Some recent fine-tuning methods…
ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
Fei Kong, Jinhao Duan, Lichao Sun +6
Though diffusion models excel in image generation, their step-by-step denoising leads to slow generation speeds. Consistency training addresses this issue with single-step sampling…
RBFormer: Improve Adversarial Robustness of Transformer by Robust Bias
Hao Cheng, Jinhao Duan, Hui Li +6
Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP). Compared with…
Semantic Adversarial Attacks via Diffusion Models
Chenan Wang, Jinhao Duan, Chaowei Xiao +3
Traditional adversarial attacks concentrate on manipulating clean examples in the pixel space by adding adversarial perturbations. By contrast, semantic adversarial attacks focus o…
Exposing the Fake: Effective Diffusion-Generated Images Detection
Ruipeng Ma, Jinhao Duan, Fei Kong +2
Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffus…
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
Jinhao Duan, Hao Cheng, Shiqi Wang +5
Large Language Models (LLMs) show promising results in language generation and instruction following but frequently "hallucinate", making their outputs less reliable. Despite Uncer…
Unlearnable Examples Give a False Sense of Data Privacy: Understanding and Relearning
Pucheng Dang, Xing Hu, Kaidi Xu +5
Unlearnable examples are proposed to prevent third parties from exploiting unauthorized data, which generates unlearnable examples by adding imperceptible perturbations to public p…
Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation
Zhengyue Zhao, Jinhao Duan, Xing Hu +6
Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can…
Improve Video Representation with Temporal Adversarial Augmentation
Jinhao Duan, Quanfu Fan, Hao Cheng +2
Recent works reveal that adversarial augmentation benefits the generalization of neural networks (NNs) if used in an appropriate manner. In this paper, we introduce Temporal Advers…
An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
Fei Kong, Jinhao Duan, RuiPeng Ma +4
Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are p…
Are Diffusion Models Vulnerable to Membership Inference Attacks?
Jinhao Duan, Fei Kong, Shiqi Wang +2
Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we…