Your enquiry has been successfully sent
Your enquiry could not be processed. Please contact us directly at www.csiro.au/Contact to make your enquiry
Biography
Dr Derek (Derui) Wang is a Senior Research Scientist at CSIRO. His research interests span adversarial robustness, neural backdoors, robustness and privacy certification, and the real-world security and privacy of machine learning systems. In particular, his work focuses on certified robustness and certified data learnability at scale, data privacy and learnability control, and red-teaming and defensive strategies for ML systems. Derek leads AI security science streams in multiple national projects, including Cyber Security Cooperative Research Centre projects on data learnability control for AI and trustworthy AI agents for cyber blue teams. He publishes regularly in leading venues such as IEEE S&P, NDSS, USENIX Security, NeurIPS, ICML, AAAI, WWW, IEEE TDSC, and IEEE TIFS. He also serve on the program committees and review boards of major international conferences and journals, including NDSS, IEEE S&P, USENIX Security, WWW, AAAI, NeurIPS, IEEE TDSC, IEEE TIFS, IEEE TNNLS, and IEEE TIP. His work has been recognized with awards such as the NDSS Distinguished Paper Award, VIC iAwards, and has been featured in major national media outlets including ABC News, 7 News, The Age, and The Sydney Morning Herald.
Other Interests
Key publications:
[1] Derui Wang, Jason Xue, Bo Li, Seyit Camtepe, and Liming Zhu, “Provably Unlearnable Data Examples,” in Network and Distributed System Security (NDSS) Symposium, 2025. (CORE A*, Distinguished Paper Award)
[2] Derui Wang, Kristen Moore, Diksha Goel, Minjune Kim, Gang Li, Yang Li, Robin Ram Mohan Doss, Jason Xue, Bo Li, Seyit Camtepe, and Liming Zhu, “CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization,” in USENIX Security Symposium, 2025. (CORE A*)
[3] Dayong Ye, Tianqing Zhu, Congcong Zhu, Derui Wang, Zewei Shi, Sheng Shen, Wanlei Zhou, and Minhui Xue, “Reinforcement Unlearning,” in Network and Distributed System Security (NDSS) Symposium, 2025. (CORE A*)
[4] Zihan Wang, Zhongkui Ma, Xinguo Feng, Zhiyang Mei, Ethan Ma, Derui Wang, Jason Xue, and Guangdong Bai, “AI Model Modulation with Logits Redistribution,” in The Web Conference (WWW), 2025. (CORE A*)
[5] Minjune Kim, Jeff Wang, Kristen Moore, Diksha Goel, Derui Wang, Ahmad Mohsin, Ahmed Ibrahim, Robin Ram Mohan Doss, Seyit Camtepe, and Helge Janicke, “CyberAlly: Leveraging LLMs and Knowledge Graphs to Empower Cyber Defenders,” in The Web Conference (WWW), 2025. (Demo Track)
[6] Youwei Shu, Xi Xiao, Derui Wang, Yuxin Cao, Siji Chen, Minhui Xue, Linyi Li, and Bo Li, “Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing,” in International Conference on Machine Learning (ICML), 2024. (CORE A*)
[7] Yuxin Cao, Ziyu Zhao, Xi Xiao, Derui Wang, Jason Xue, and Jin Lu, “LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer,” in 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024. (CORE A*)
[8] Diksha Goel, Kristen Moore, Mingyu Guo, Derui Wang, Minjune Kim, and Seyit Camtepe, “Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning,” in European Symposium on Research in Computer Security (ESORICS), 2024. (CORE A)
[9] Yuxin Cao, Yian Li, Yumeng Zhu, Derui Wang, and Jason Xue, “Flow-Attention-Based Spatio-Temporal Aggregation Network for 3D Mask Detection,” in Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS), 2024. (CORE A*)
[10] Yuxin Cao, Xi Xiao, Ruoxi Sun, Derui Wang, Minhui Xue, and Sheng Wen, “StyleFool: Fooling Video Classification Systems via Style Transfer,” in IEEE Symposium on Security and Privacy (Oakland), 2023. (CORE A*)
[11] Wanlun Ma, Derui Wang, Ruoxi Sun, Minhui Xue, Sheng Wen, and Yang Xiang, “The ‘Beatrix’ Resurrections: Robust Backdoor Detection via Gram Matrices,” in Network and Distributed System Security (NDSS) Symposium, 2023. (CORE A*)
[12] Derui Wang, Chaoran Li, Sheng Wen, Qing-Long Han, Surya Nepal, Xiangyu Zhang, and Yang Xiang, “Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examples,” IEEE Transactions on Cybernetics, vol. 52, no. 8, pp. 7427–7440, 2022. (CORE A)
[13] Chaoran Li, Xiao Chen, Derui Wang, Sheng Wen, Ejaz Ahmed, Seyit Camtepe, and Yang Xiang, “Backdoor Attack on Machine Learning-Based Android Malware Detectors,” IEEE Transactions on Dependable and Secure Computing, vol. 14, 2021. (CORE A)
[14] Derui Wang, Chaoran Li, Sheng Wen, Surya Nepal, and Yang Xiang, “Man-in-the-Middle Attacks Against Machine Learning Classifiers via Malicious Generative Models,” IEEE Transactions on Dependable and Secure Computing, vol. 18, no. 5, pp. 2074–2087, 2020. (CORE A)
[15] Derui Wang, Chaoran Li, Sheng Wen, Surya Nepal, and Yang Xiang, “Defending Against Adversarial Attack Towards Deep Neural Networks via Collaborative Multi-Task Training,” IEEE Transactions on Dependable and Secure Computing, pp. 1–12, 2020. (CORE A)
[16] Yansong Gao, Change Xu, Derui Wang, Shiping Chen, Damith C Ranasinghe, and Surya Nepal, “STRIP: A Defence against Trojan Attacks on Deep Neural Networks,” in 35th Annual Computer Security Applications Conference (ACSAC), 2019. (CORE A)
Achievements and Awards
-
2025-2025
Distinguished Paper Award
NDSS Symposium 2025 -
2025-2025
Data61 SCS Science Excellence Award
CSIRO's Data61 -
2025-2025
Data61 SCS Collaboration Award
CSIRO's Data61 -
2025-2025
VIC iAwards
Australian Information Industry Association (AIIA) -
2017-2020
CSIRO's Data61 Scholarship
CSIRO's Data61 -
2006-2006
Third Prize, Chinese Physics Olympiad
Chinese Physical Society