Yunruo Zhang — accepted AI-conference papers

2025

DROWN: Towards Tighter LiRPA-based Robustness Certification

Yunruo Zhang, Tianyu Du, Shouling Ji, Shanqing Guo

COLING 2025main

The susceptibility of deep neural networks to adversarial attacks is a well-established concern. To address this problem, robustness certification is proposed, which, unfortunately, suffers from precision or scalability issues. In this paper, we present DROWN (Dual CROWN), a novel method for certify…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

GaLileo: General Linear Relaxation Framework for Tightening Robustness Certification of Transformers

Yunruo Zhang, Lujia Shen, Shanqing Guo, Shouling Ji

AAAI 2024technical

Transformers based on attention mechanisms exhibit vulnerability to adversarial examples, posing a substantial threat to the security of their applications. Aiming to solve this problem, the concept of robustness certification is introduced to formally ascertain the presence of any adversarial examp…

Cited by 4 Source ↗PDF ↗Scholar ↗