7 papers
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
Jiali Wei, Ming Fan, Mingkun Zhang +6
MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may reside in images, texts, or bot…
RAE-NWM: Navigation World Model in Dense Visual Representation Space
Mingkun Zhang, Wangtian Shen, Fan Zhang +3
Visual navigation requires agents to reach goals in complex environments through perception and planning. World models address this task by simulating action-conditioned state tran…
NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
Junjie Nan, Jianing Li, Wei Chen +2
Adversarial purification has achieved great success in combating adversarial image perturbations, which are usually assumed to be additive. However, non-additive adversarial pertur…
CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
Mingkun Zhang, Keping Bi, Wei Chen +2
In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-sho…
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
Mingkun Zhang, Keping Bi, Wei Chen +3
Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated…
Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information
Mingkun Zhang, Jianing Li, Wei Chen +2
Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have a…
Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off
Yu-An Liu, Ruqing Zhang, Mingkun Zhang +4
Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted b…