Work

Improving Adversarial Training From the Perspective of Class-Flipping Distribution

Year: 2025

Type: article

Source: IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI: 10.1109/tpami.2025.3540200

Authors: Dawei Zhou, Nannan Wang, Tongliang Liu, Xinbo Gao

Institutions: Xidian University, The University of Sydney, Chongqing University of Posts and Telecommunications

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funders: National Natural Science Foundation of China, Australian Research Council, Fundamental Research Funds for the Central Universities

Awards: Modelling Adversarial Noise for Trustworthy Data Analytics, Visual methods for advanced automation of underwater manipulation, G2452297484, ARC Training Centre in Data Analytics for Resources and Environments (DARE), G4297946667, Self-supervised feature learning for rapid processing of marine imagery, Transfer Learning Handling Causally Bilateral Shift , G913836228

OpenAlex ID: W4407316677

FWCI: 2.464

Cites: 74

Cited by: 6

Related to: 10