10 papers
DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging
Jiayang Zhang, Ji Guo, Jiachen Li +2
Unconditional diffusion checkpoint merging assumes benign sources, yet a compromised public checkpoint can transfer a dormant backdoor while clean generation appears normal. Mitiga…
State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
Ji Guo, Wenbo Jiang, Yansong Lin +6
Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new…
CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models
Ji Guo, Xiaolong Qin, Cencen Liu +3
Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as their applications become increasi…
AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution
Cencen Liu, Dongyang Zhang, Wen Yin +6
Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synth…
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
Guanyu Hou, Jiaming He, Yinhang Zhou +4
Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This…
TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model
Ji Guo, Peihong Chen, Wenbo Jiang +6
Multimodal diffusion models for image editing generate outputs conditioned on both textual instructions and visual inputs, aiming to modify target regions while preserving the rest…