Hi! Welcome to my homepage.

I am a Postdoc researcher working with Prof.Holger Hermanns and Prof. Lijun Zhang since November 2023. Currently, I am working on the project of Explainable Intelligent Systems, as well as a project about the adversarial attack against 3D object detection in autonomous driving.

From July 2021 to July 2023, I served as a Post-doctoral researcher on QARMA team of LIS Marseille, working on Interpretability of Deep Neural Network with Ronan Sicre, and Yannis Avrithis.

I defended my Ph.D thesis “Deep Learning in Adversarial Context” on June 17 2021. My Ph.D was supervised by Laurent Amsaleg, Yannis Avrithis and Teddy Furon in the Linkmedia team at IRISA Rennes. My diploma is from PRogram Of Sino-French Education for Research (PROSFER) between East China Normal University and École normale supérieure de Rennes. During the Ph.D, my research focus on the security problem in machine learning. Currently my work has mainly focused on trustworthy AI.

Before coming to IRISA, I worked on Multi-objective Evolutionary Computation with Aimin Zhou from 2015-2017. And I received my bachelor’s degree in 2015 from Department of Computer Science and Technology, East China Normal University.

Publications

• “Revisiting Transferable Adversarial Image Examples: Attack Categorization, Evaluation Guidelines, and New Insights” Z Zhao, H Zhang, R Li, R Sicre, L Amsaleg, M Backes, Q Li, C Shen, arXiv preprint arXiv:2310.11850, 2023.
• “Opti-CAM: Optimizing saliency maps for interpretability” H Zhang, F Torres, R Sicre, Y Avrithis, S Ayache, arXiv preprint arXiv:2301.07002, 2023.
• “Patch Replacement: A Transformation-based Method to Improve Robustness against Adversarial Attacks” H Zhang, Y Avrithis, T Furon, L Amsaleg, Proceedings of the 1st International Workshop on Trustworthy AI for Multimedia Computing, 9-17, 2021.
• “Walking on the Edge: Fast, Low-Distortion Adversarial Examples” H Zhang, Y Avrithis, T Furon, L Amsaleg, IEEE Transactions on Information Forensics and Security 16, 701-713, 2020.
• “Smooth Adversarial Examples” H Zhang, Y Avrithis, T Furon, L Amsaleg, EURASIP Journal on Information Security (1), 1-12, 2020.
• “Tree-Structured Decomposition and Adaptation in MOEA/D” H Zhang, A Zhou, International Conference on Parallel Problem Solving from Nature, 359-371, 2018.
• “Accelerating MOEA/D by Nelder-Mead method” H Zhang, A Zhou, G Zhang, HK Singh, 2017 IEEE Congress on Evolutionary Computation (CEC), 976-983, 2017.