5 papers · 1 filter
DuMo: Dual Encoder Modulation Network for Precise Concept Erasure
Feng Han, Kai Chen, Chao Gong +3
The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copy…
TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
Xin Wang, Kai Chen, Jiaming Zhang +2
Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have sh…
Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
Chao Gong, Kai Chen, Zhipeng Wei +2
Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing i…
ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack
Ziyi Gao, Kai Chen, Zhipeng Wei +5
Recent diffusion-based unrestricted attacks generate imperceptible adversarial examples with high transferability compared to previous unrestricted attacks and restricted attacks.…
AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
Xin Wang, Kai Chen, Xingjun Ma +3
Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks even under a black-box setting where the adversary can only query the model. Particularly, query-based…