Scalable Attribution of Adversarial Attacks via Multi-Task Learning

no code implementations • 25 Feb 2023 • Zhongyi Guo, Keji Han, Yao Ge, Wei Ji, Yun Li

In this paper, AAP is defined as the recognition of three signatures, i. e., {\em attack algorithm}, {\em victim model} and {\em hyperparameter}.

Multi-Task Learning

Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training

1 code implementation • ICCV 2023 • Yao Ge, Yun Li, Keji Han, Junyi Zhu, Xianzhong Long

However, they are susceptible to adversarial examples, which are generated by adding adversarial perturbations to original data.

Is It Time to Redefine the Classification Task for Deep Learning Systems?

no code implementations • ICML Workshop AML 2021 • Keji Han, Yun Li, Songcan Chen

Many works have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial examples.

Adversarial Attack Classification

Learning Task-aware Robust Deep Learning Systems

no code implementations • 11 Oct 2020 • Keji Han, Yun Li, Xianzhong Long, Yao Ge

Many works demonstrate that deep learning system is vulnerable to adversarial attack.

Adversarial Attack General Classification