The mailman list for the reading group is “ml-security”. To subscribe, visit:
https://engineering.purdue.edu/ECN/mailman/listinfo/ml-security
For Fall 2021, we will be meeting on Thursdays 5:00-6:30. We will start off virtually and then hopefully, with the case numbers coming down, we will move to in-person.
Dates | Topic | Suggested papers | Presenters | Recording |
---|---|---|---|---|
Sep 6 | Introductions, Fun quiz, Paper writing tips | Saurabh | ||
Sep 16 | Own work: Ensemble security for ML | Ruqi | ||
Sep 23, 30 | Reliability of zero/one shot learning | A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts (CVPR, 2018) | Ashraf | Recording (protected) Slide deck |
Oct 7 | Model extraction attacks and defenses | Tramèr, Florian, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. "Stealing machine learning models via prediction apis." In 25th {USENIX} Security Symposium ({USENIX} Security 16), pp. 601-618. 2016. | Ahaan, Atul | Recording (protected) Slide deck |
Oct 14 | October break | |||
Oct 21, 28 | Security of distributed learning | Liu, Lumin, Jun Zhang, S. H. Song, and Khaled B. Letaief. "Client-edge-cloud hierarchical federated learning." In ICC 2020-2020 IEEE International Conference on Communications (ICC), pp. 1-6. IEEE, 2020. Wang, Xiaoding, Sahil Garg, Hui Lin, Jia Hu, Georges Kaddoum, Md Jalil Piran, and M. Shamim Hossain. "Towards accurate anomaly detection in industrial internet-of-things using hierarchical federated learning." IEEE Internet of Things Journal (2021). | Edgardo, Josh Z | Slide deck |
Nov 4 | Own work | Akhil | Video (Password protected) |
|
Nov 11 | Large streaming models on tiny devices | "Flexible High-resolution Object Detection on Edge Devices with Tunable Latency" MSRA, USTC, Tsinghua, Mobicom 2021. "MoViNets: Mobile Video Networks for Efficient Video Recognition" Google Research, CVPR 2021. | Pengcheng, Preeti | Pengcheng: Mobicom 2021 Preeti: CVPR 2021 |
Nov 18 | Own work: Approximate streaming models on embedded devices | Akash, Sarthak | ||
Nov 25 | Thanksgiving break | |||
Dec 2 | Own work | Mustafa | ||
Dec 9 | Adversarial reinforcement learning | Pinto, Lerrel, James Davidson, Rahul Sukthankar, and Abhinav Gupta. "Robust adversarial reinforcement learning." In International Conference on Machine Learning, pp. 2817-2826. PMLR, 2017. Gleave, Adam, Michael Dennis, Cody Wild, Neel Kant, Sergey Levine, and Stuart Russell. "Adversarial policies: Attacking deep reinforcement learning." ICLR 2020. | Dipesh | Slide Video (protected) |
For Spring 2021, we will be meeting on Tuesdays 11.30-1.00.
The papers are samples and the discussion will go beyond them or may use other papers altogether.
Date | Topic | Presenters |
---|---|---|
Jan 26, Feb 2 | How to write a strong evaluation section | Saurabh |
Feb 9 | Lightning talks from all group members | All |
Feb 16 | Own work: Security of Android devices | Josh |
Feb 23, Mar 2 | Reliability and security of serverless computing Sreekanti et al. "A Fault-Tolerance Shim for Serverless Computing" Eurosys 2020. Datta et al. "Valve: Securing Function Workflows on Serverless Computing Platforms" WWW 2020. | Karthick, Ashraf |
Mar 9 | Own work: IoT deployments | Pengcheng, Edgardo |
Mar 16, 23 | Reliable computing with heterogeneous embedded devices and drones | Ran, Jay |
Mar 30 | Own work: Security in distributed ML | Atul |
Apr 6, 20 (Apr 13 is reading day and off for students) | Distributed ML on lightweight devices | Pranjal, Tanushree |
Apr 27 | Own work: Security in ML | Ruqi |
May 4 | Lessons learned | Saurabh |
History of DCSL Reading group
2016-20, 2015, 2014, 2013, 2012, 2010, 2009, 2008, 2007, 2006, 2005, 2004, 2003, 2002