9/13 | Differentially private machine learning <br>**Reading:** [*On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches*](https://arxiv.org/pdf/1708.08022) <br>**Reading:** [*Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data*](https://arxiv.org/pdf/1610.05755) | |
9/18 | Adversarial examples <br>**Reading:** [*Intriguing Properties of Neural Networks*](https://arxiv.org/pdf/1312.6199.pdf) <br>**Reading:** [*Explaining and Harnessing Adversarial Examples*](https://arxiv.org/abs/1412.6572) <br>**Reading:** [*Robust Physical-World Attacks on Deep Learning Models*](https://arxiv.org/pdf/1707.08945.pdf) | |
9/20 | Data poisoning <br>**Reading:** [*Poisoning Attacks against Support Vector Machines*](https://arxiv.org/pdf/1206.6389) | |
9/23 | Defenses and detection: challenges <br>**Reading:** [*Towards Evaluating the Robustness of Neural Networks*](https://arxiv.org/pdf/1608.04644.pdf) <br>**Reading:** [*Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods*](https://arxiv.org/pdf/1705.07263.pdf) | JH |
9/25 | Certified defenses <br>**Reading:** [*Certified Defenses for Data Poisoning Attacks*](https://arxiv.org/pdf/1706.03691.pdf) <br>**Reading:** [*Certified Defenses against Adversarial Examples*](https://arxiv.org/pdf/1801.09344) | |
9/27 | Adversarial training <br>**Reading:** [*Towards Deep Learning Models Resistant to Adversarial Attacks*](https://arxiv.org/pdf/1706.06083.pdf) | |
10/2 | SMC for machine learning <br>**Reading:** [*Secure Computation for Machine Learning With SPDZ*](https://arxiv.org/pdf/1901.00329) <br>**Reading:** [*Helen: Maliciously Secure Coopetitive Learning for Linear Models*](https://arxiv.org/pdf/1907.07212) | |
10/4 | Secure data collection at scale <br>**Reading:** [*Prio: Private, Robust, and Scalable Computation of Aggregate Statistics*](https://people.csail.mit.edu/henrycg/files/academic/papers/nsdi17prio.pdf) | |
10/7 | Verifiable computing <br>**Reading:** [*SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud*](https://arxiv.org/pdf/1706.10268) | JH |
10/9 | Side channels and implementation issues <br>**Reading:** [*On Significance of the Least Significant Bits For Differential Privacy*](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.366.5957&rep=rep1&type=pdf) | |
10/11 | Model watermarking <br>**Reading:** [*Protecting Intellectual Property of Deep Neural Networks with Watermarking*](https://gzs715.github.io/pubs/WATERMARK_ASIACCS18.pdf) <br>**Reading:** [*Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring*](https://arxiv.org/pdf/1802.04633) | | MS1 Due
10/14 | Overview and basic notions <br>**Reading:** Chapter 2 from [Barocas, Hardt, and Narayanan](https://fairmlbook.org/demographic.html) | JH |
10/16 | Individual and group fairness <br>**Reading:** [*Fairness through Awarness*](https://arxiv.org/pdf/1104.3913) <br>**Reading:** [*Equality of Opportunity in Supervised Learning*](https://arxiv.org/pdf/1610.02413) | |
10/18 | Inherent tradeoffs <br>**Reading:** [*Inherent Trade-Offs in the Fair Determination of Risk Scores*](https://arxiv.org/pdf/1609.05807) | |
10/21 | Defining fairness: challenges <br>**Reading:** [*50 Years of Test (Un)fairness: Lessons for Machine Learning*](https://arxiv.org/pdf/1811.10104) | JH |
10/23 | Fairness in unsupervised learning <br>**Reading:** [*Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings*](https://arxiv.org/pdf/1607.06520) <br>**Reading:** [*Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints*](https://arxiv.org/pdf/1707.09457) | |
| <center><h4>**Advanced Topic: PL and Verification**</h4></center> | |
10/28 | Overview and basic notions | JH |
10/30 | Probabilistic programming languages <br>**Reading:** [*Probabilistic Programming*](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/fose-icse2014.pdf) | |
11/1 | Automata learning and interpretability <br>**Reading:** [*Model Learning*](https://m-cacm.acm.org/magazines/2017/2/212445-model-learning/fulltext) <br>**Reading:** [*Interpreting Finite Automata for Sequential Data*](https://arxiv.org/pdf/1611.07100) | |
11/4 | Programming languages for differential privacy <br>**Reading:** [*Programming Language Techniques for Differential Privacy*](https://dl.acm.org/citation.cfm?id=2893591&dl=ACM&coll=DL) | JH |
11/6 | Verifying neural networks <br>**Reading:** [*AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation*](https://files.sri.inf.ethz.ch/website/papers/sp2018.pdf) <br>**Reading:** [*DL2: Training and Querying Neural Networks with Logic*](http://proceedings.mlr.press/v97/fischer19a/fischer19a.pdf) | |
11/8 | Verifying probabilistic programs <br>**Reading:** [*Advances and Challenges of Probabilistic Model Checking*](https://www.prismmodelchecker.org/papers/allerton10.pdf) <br>**Reading:** [*A Program Logic for Union Bounds*](https://arxiv.org/pdf/1602.05681) | | MS2 Due
| <center><h4>**No Lectures: Work on Projects**</h4></center> | |
