← Search

Cong Zou

2 accepted papers

2024

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks

CVPR 2024poster

Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility. Existing defense methods which rely on attack data or prior knowledge struggle to effectively address a wide range of adversarial patches. In this paper we show two inherent char…

2023

The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data

ICCV 2023oral

Recently, backdoor attacks have posed a serious security threat to the training process of deep neural networks (DNNs). The attacked model behaves normally on benign samples but outputs a specific result when the trigger is present. However, compared with the rocketing progress of backdoor attacks,…

Cited by 5PDFcodeScholar