4 papers · 1 filter
Under the Skin: Backdoor Infection in Multimodal Large Language Models
Jiawen Wang, Ruo Yang, Haoran Dai +2
Multimodal Large Language Models (MLLMs) have achieved impressive performance in generating text conditioned on inputs from different modalities. In this work, we introduce backdoo…
Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models
Haoran Dai, Jiawen Wang, Ruo Yang +4
Text-to-image diffusion models (T2I DMs) have achieved remarkable success in generating high-quality and diverse images from text prompts, yet recent studies have revealed their vu…
From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs
Jiawen Wang, Pritha Gupta, Ivan Habernal +3
Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to attacks that generate harmful or sensitive outputs. As open-source LLMs are increasingly adopted in h…
Backdoor Attacks on Discrete Graph Diffusion Models
Jiawen Wang, Samin Karim, Samin Bin Karim +2
Diffusion models have demonstrated remarkable generative capabilities in continuous data domains such as images and videos. Recently, discrete graph diffusion models (DGDMs) have e…