Geguang Pu (蒲戈光)

Geguang Pu (蒲戈光)

Professor and Execution Dean of Software Engineering Institute, East China Normal University.

Posts by Collection

portfolio

publications

ALA: Naturalness-aware Adversarial Lightness Attack

Published in ACM Multimedia 2023, 2023

The proposed Adversarial Lightness Attack(ALA), a white-box unrestricted adversarial attack that focuses on modifying the lightness of the images, is to enhance the robustness of deep neural networks from a more natural way.

Recommended citation: Yihao Huang, Liangru Sun, Qing Guo, Felix Juefei-Xu, Jiayi Zhu, Jincao Feng, Yang Liu, Geguang Pu. (2023). "ALA: Naturalness-aware Adversarial Lightness Attack." ACM Multimedia 2023.

Searching for i-Good Lemmas to Accelerate Safety Model Checking

Published in CAV 2023, 2023

A new insight for improving the performance of SAT-based model checking. The definition of i-Good lemmas is simple but general, that can be proved to be effective in all state-of-the art model checkers, like Nu-XMV, IC3/PDR and SimpleCAR.

Recommended citation: Yechuan Xia, Anna Becchi, Alessandro Cimatti, Alberto Griggio, Jianwen Li, Geguang Pu. (2023). "Searching for i-Good Lemmas to Accelerate Safety Model Checking." CAV 2023.

Property-Based Testing for Validating User Privacy-Related Functionalities in Social Media Apps

Published in SIGSOFT FSE Industry Track 2024, 2024

This paper designs a property-based testing method to validate app behaviors against the properties described by the given privacy specifications.

Recommended citation: Jingling Sun, Ting Su, Jun Sun, Jianwen Li, Mengfei Wang, Geguang Pu. (2024). "Property-Based Testing for Validating User Privacy-Related Functionalities in Social Media Apps." SIGSOFT FSE Industry Track 2024.

talks

teaching