We put a tentative syllabus here to give you an idea what future may bring. This syllabus is subject to change as the course progresses.
| # | Day | Date | Topic | Assignment | Speakers |
|---|---|---|---|---|---|
| 1 | Tue | Jan 21 | Introduction | Form reading group | |
| 2 | Tue | Jan 28 | Deep learning | Read Lecun-90c, AlexNet | |
| 3 | Tue | Feb 4 | Adversarial ML (1) | Read Intriguing properties of neural networks, FGSM attack | |
| 4 | Tue | Feb 11 | Adversarial ML (2) | Read PGD attack, Obfuscated gradients not useful | |
| 5 | Tue | Feb 18 | Adversarial ML (3) | Read Unrestricted attack, Blackbox attack | |
| 6 | Tue | Feb 25 | Testing DL | Read DeepXplore, VeriVis | |
| 7 | Tue | Mar 3 | Verifying DL (1) | Read Reluplex, DeepSafe | |
| 8 | Tue | Mar 10 | Cancelled (due to COVID-19) | ||
| 9 | Tue | Mar 17 | No class (Spring recess) | ||
| 10 | Tue | Mar 24 | |
Read Reluval, Neurify | Guest: Shiqi Wang |
| 11 | Tue | Mar 31 | Verifying DL (3) | Read AI2, Abstract domain | |
| 12 | Tue | Apr 7 | Robustness training | Read Stability training, Adversarial logit training | |
| 13 | Tue | Apr 14 | Robustness tradeoffs | Read Robustness vs accuracy, Adversarial examples are features | |
| 14 | Tue | Apr 21 | NN architectures | Read Gated graph NN, BERT | |
| 15 | Tue | Apr 28 | Mini-research conference | Present and demo your final project |