Our Faculty

headshot of Adnan Siraj Rakin

Adnan Siraj Rakin

Assistant Professor

Computer Science

Background

Adnan Siraj Rakin received his PhD in computer engineering from Arizona State University (ASU) in 2022. He also completed his MS degree in computer engineering from ASU in 2021. Before his graduate studies, he completed his BS degree in electrical and electronic engineering (EEE) from the Bangladesh University of Engineering and Technology in 2016. 

His research interest focuses on AI security, where he has been the author/co-author of notable publications on IEEE/ACM top-tier journals and conferences, including CVPR, ICCV, T-PAMI, USENIX Security and IEEE S&P. ‚Äč

Google Scholar

Recent Publications
Adnan Siraj Rakin
, Md Hafizul Islam Chowdhuryy, Fan Yao, and Deliang Fan. "Deepsteal: Advanced model extractions leveraging efficient weight stealing in memories." In 2022 IEEE Symposium on Security and Privacy (SP), pp. 1157-1174.
IEEE, 2022.

Adnan Siraj Rakin, Ye Wang, Shuchin Aeron, Toshiaki Koike-Akino, Pierre Moulin, and Kieran Parsons. "Towards Universal Adversarial Examples and Defenses." In 2021 IEEEInformation Theory Workshop (ITW), pp. 1-6. IEEE, 2021.

Adnan Siraj Rakin, Zhezhi He, Jingtao Li, Fan Yao, Chaitali Chakrabarti, and Deliang Fan. "T-bfa: Targeted bit-flip adversarial weight attack." IEEE Transactions on Pattern
Analysis and Machine Intelligence (2021).

Adnan Siraj Rakin, Yukui Luo, Xiaolin Xu, and Deliang Fan. "{Deep-Dup}: An adversarial
weight duplication attack framework to crush deep neural network in {Multi-Tenant}{FPGA}." In 30th USENIX Security Symposium (USENIX Security 21), pp. 1919-
1936. 2021.

Adnan Siraj Rakin, Zhezhi He, Li Yang, Yanzhi Wang, Liqiang Wang, and Deliang Fan. "Robust sparse regularization: Defending adversarial attacks via regularized sparse
network." In Proceedings of the 2020 on Great Lakes Symposium on VLSI, pp. 125-130. 2020.

Adnan Siraj Rakin, He, Zhezhi, Jingtao Li, Chaitali Chakrabarti, and Deliang Fan. "Defending and harnessing the bit-flip based adversarial weight attack." In Proceedings
of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14095-14103. 2020.

Adnan Siraj Rakin
, Zhezhi He, and Deliang Fan. "Tbt: Targeted neural network attack with bit trojan." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13198-13207. 2020.

Adnan Siraj Rakin, Zhezhi He, and Deliang Fan. "Bit-flip attack: Crushing neural network with progressive bit search." In Proceedings of the IEEE/CVF International Conference
on Computer Vision, pp. 1211-1220. 2019.

Adnan Siraj Rakin. He, Zhezhi and Deliang Fan. "Parametric noise injection: Trainable randomness to improve deep neural network robustness against adversarial attack." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
Recognition, pp. 588-597. 2019.

Adnan Siraj Rakin, Shaahin Angizi, Zhezhi He, and Deliang Fan. "PIM-TGAN: A processing-in-memory accelerator for ternary generative adversarial networks." In 2018 IEEE 36th International Conference on Computer Design (ICCD), pp. 266-273. IEEE, 2018.

Education

  • PhD and MS, computer engineering, Arizona State University 
  • BS, electrical and electronic engineering, Bangladesh University of Engineering and Technology

Research Interests

  • Security of deep learning algorithms
  • Adversarial weight attacks and defenses
  • Adversarial input attacks and defenses
  • Model stealing attacks using memory side-channel
  • Computer vision algorithms for efficient on-device learning
  • Exploring hardware (e.g., FPGA/CPU/GPU) vulnerabilities using novel adversarial attack algorithms
  • Efficient implementation of machine learning framework