1 code implementation • 25 Apr 2024 • Lihua Jing, Rui Wang, Wenqi Ren, Xin Dong, Cong Zou
Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility.
1 code implementation • ICCV 2023 • Zixuan Zhu, Rui Wang, Cong Zou, Lihua Jing
This inspires us to propose a novel dual-network training framework: The Victim and The Beneficiary (V&B), which exploits a poisoned model to train a clean model without extra benign samples.
no code implementations • 11 Aug 2023 • Xin Dong, Rui Wang, Siyuan Liang, Aishan Liu, Lihua Jing
As for the weak black-box scenario feasibility, we obverse that representations of the average feature in multiple face recognition models are similar, thus we propose to utilize the average feature via the crawled dataset from the Internet as the target to guide the generation, which is also agnostic to identities of unknown face recognition systems; in nature, the low-frequency perturbations are more visually perceptible by the human vision system.