diff --git a/website/docs/schedule/lectures.md b/website/docs/schedule/lectures.md index 40e5489..7e74806 100644 --- a/website/docs/schedule/lectures.md +++ b/website/docs/schedule/lectures.md @@ -8,34 +8,34 @@ 9/7 |
**NO CLASS: LABOR DAY**
| | | 9/9 | Composition and closure properties
**Reading:** [Dwork and Roth](https://www.cis.upenn.edu/~aaroth/Papers/privacybook.pdf) 3.5 | Justin | --- | [Signups](https://docs.google.com/spreadsheets/d/1Qiq6RtBiHD6x7t-wPqAykvTDdbbBvZYSMZ9FrKUHKm4/edit?usp=sharing) Due 9/11 | What does differential privacy actually mean?
**Reading:** [Lunchtime for Differential Privacy](https://github.com/frankmcsherry/blog/blob/master/posts/2016-08-16.md) | Justin | --- | -9/14 | Private machine learning
**Reading:** [*On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches*](https://arxiv.org/pdf/1708.08022)
**Reading:** [*Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data*](https://arxiv.org/pdf/1610.05755) | --- | --- | -9/16 | Privately generating synthetic data
**Reading:** [*A Simple and Practical Algorithm for Differentially Private Data Release*](https://papers.nips.cc/paper/4548-a-simple-and-practical-algorithm-for-differentially-private-data-release.pdf)
**Reading:** [*Private Post-GAN Boosting*](https://arxiv.org/abs/2007.11934) | --- | --- | +9/14 | Private machine learning
**Reading:** [*On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches*](https://arxiv.org/pdf/1708.08022)
**Reading:** [*Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data*](https://arxiv.org/pdf/1610.05755) | | | +9/16 | Privately generating synthetic data
**Reading:** [*A Simple and Practical Algorithm for Differentially Private Data Release*](https://papers.nips.cc/paper/4548-a-simple-and-practical-algorithm-for-differentially-private-data-release.pdf)
**Reading:** [*Private Post-GAN Boosting*](https://arxiv.org/abs/2007.11934) | | | |

**Adversarial Machine Learning**

| | 9/18 | Overview and basic concepts | Justin | --- | -9/21 | Adversarial examples
**Reading:** [*Intriguing Properties of Neural Networks*](https://arxiv.org/pdf/1312.6199.pdf)
**Reading:** [*Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples*](https://arxiv.org/abs/1605.07277)
**See also:** [*Explaining and Harnessing Adversarial Examples*](https://arxiv.org/pdf/1412.6572) | --- | --- | -9/23 | Data poisoning
**Reading:** [*Poisoning Attacks against Support Vector Machines*](https://arxiv.org/pdf/1206.6389)
**Reading:** [*Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks*](https://arxiv.org/pdf/1804.00792) | --- | --- | +9/21 | Adversarial examples
**Reading:** [*Intriguing Properties of Neural Networks*](https://arxiv.org/pdf/1312.6199.pdf)
**Reading:** [*Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples*](https://arxiv.org/abs/1605.07277)
**See also:** [*Explaining and Harnessing Adversarial Examples*](https://arxiv.org/pdf/1412.6572) | | | +9/23 | Data poisoning
**Reading:** [*Poisoning Attacks against Support Vector Machines*](https://arxiv.org/pdf/1206.6389)
**Reading:** [*Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks*](https://arxiv.org/pdf/1804.00792) | | | 9/25 | Defenses and detection: challenges
**Reading:** [*Towards Evaluating the Robustness of Neural Networks*](https://arxiv.org/pdf/1608.04644.pdf)
**Reading:** [*Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods*](https://arxiv.org/pdf/1705.07263.pdf) | Justin | --- | -9/28 | Certified defenses
**Reading:** [*Certified Defenses for Data Poisoning Attacks*](https://arxiv.org/pdf/1706.03691.pdf)
**Reading:** [*Certified Defenses against Adversarial Examples*](https://arxiv.org/pdf/1801.09344) | --- | --- | -9/30 | Adversarial training
**Reading:** [*Towards Deep Learning Models Resistant to Adversarial Attacks*](https://arxiv.org/pdf/1706.06083.pdf)
**See also:** [*Ensemble Adversarial Training: Attacks and Defenses*](https://arxiv.org/pdf/1705.07204) | --- | --- | +9/28 | Certified defenses
**Reading:** [*Certified Defenses for Data Poisoning Attacks*](https://arxiv.org/pdf/1706.03691.pdf)
**Reading:** [*Certified Defenses against Adversarial Examples*](https://arxiv.org/pdf/1801.09344) | | | +9/30 | Adversarial training
**Reading:** [*Towards Deep Learning Models Resistant to Adversarial Attacks*](https://arxiv.org/pdf/1706.06083.pdf)
**See also:** [*Ensemble Adversarial Training: Attacks and Defenses*](https://arxiv.org/pdf/1705.07204) | | | |

**Applied Cryptography**

| | | 10/2 | Overview and basic constructions
**Reading:** [Boneh and Shoup](http://toc.cryptobook.us/), 11.6, 19.4
**See also:** [Evans, Kolesnikov, and Rosulek](https://securecomputation.org/), Chapter 3 | Justin | --- | -10/5 | Secure data collection at scale
**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
**Reading:** [*SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud*](https://arxiv.org/pdf/1706.10268) | --- | --- | -10/9 | Side channels and implementation issues
**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) | --- | --- | -10/12 | Model watermarking
**Reading:** [*Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring*](https://arxiv.org/pdf/1802.04633)
**See also:** [*Protecting Intellectual Property of Deep Neural Networks with Watermarking*](https://gzs715.github.io/pubs/WATERMARK_ASIACCS18.pdf) | --- | --- | MS1 Due +10/5 | Secure data collection at scale
**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
**Reading:** [*SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud*](https://arxiv.org/pdf/1706.10268) | | | +10/9 | Side channels and implementation issues
**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) | | | +10/12 | Model watermarking
**Reading:** [*Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring*](https://arxiv.org/pdf/1802.04633)
**See also:** [*Protecting Intellectual Property of Deep Neural Networks with Watermarking*](https://gzs715.github.io/pubs/WATERMARK_ASIACCS18.pdf) | | | MS1 Due |

**Algorithmic Fairness**

| | | 10/14 | Overview and basic notions
**Reading:** [Barocas, Hardt, and Narayanan](https://fairmlbook.org/index.html), Chapter 1-2
**See also:** [*50 Years of Test (Un)fairness: Lessons for Machine Learning*](https://arxiv.org/pdf/1811.10104) | Justin | --- | -10/16 | Individual and group fairness
**Reading:** [*Fairness through Awarness*](https://arxiv.org/pdf/1104.3913)
**Reading:** [*Equality of Opportunity in Supervised Learning*](https://arxiv.org/pdf/1610.02413) | --- | --- | -10/19 | Inherent tradeoffs
**Reading:** [*Inherent Trade-Offs in the Fair Determination of Risk Scores*](https://arxiv.org/pdf/1609.05807) | --- | --- | +10/16 | Individual and group fairness
**Reading:** [*Fairness through Awarness*](https://arxiv.org/pdf/1104.3913)
**Reading:** [*Equality of Opportunity in Supervised Learning*](https://arxiv.org/pdf/1610.02413) | | | +10/19 | Inherent tradeoffs
**Reading:** [*Inherent Trade-Offs in the Fair Determination of Risk Scores*](https://arxiv.org/pdf/1609.05807) | | | 10/21 | Fairness and causality
**Reading:** [Barocas, Hardt, and Narayanan](https://fairmlbook.org/causal.html), Chapter 4 | Justin | --- | -10/23 | Fairness in unsupervised learning
**Reading:** [*Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings*](https://arxiv.org/pdf/1607.06520)
**See also:** [*Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints*](https://arxiv.org/pdf/1707.09457) | --- | --- | +10/23 | Fairness in unsupervised learning
**Reading:** [*Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings*](https://arxiv.org/pdf/1607.06520)
**See also:** [*Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints*](https://arxiv.org/pdf/1707.09457) | | | 10/26 | Testing fairness, empirically
**Reading:** [Barocas, Hardt, and Narayanan](https://fairmlbook.org/causal.html), Chapter 5 | Justin | --- | |

**PL and Verification**

| | | 10/28 | Overview and basic notions | Justin | --- | -10/30 | Probabilistic programming languages
**Reading:** [*Probabilistic Programming*](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/fose-icse2014.pdf) | --- | --- | -11/2 | Verifying probabilistic programs
**Reading:** [*A Program Logic for Union Bounds*](https://arxiv.org/pdf/1602.05681)
**See also:** [*Advances and Challenges of Probabilistic Model Checking*](https://www.prismmodelchecker.org/papers/allerton10.pdf) | --- | --- | -11/4 | Languages for differential privacy
**Reading:** [*Distance Makes the Types Grow Stronger: A Calculus for Differential Privacy*](https://www.cis.upenn.edu/~bcpierce/papers/dp.pdf)
**See also:** [*Programming Language Techniques for Differential Privacy*](https://siglog.hosting.acm.org/wp-content/uploads/2016/01/siglog_news_7.pdf) | --- | --- | -11/6 | Verifying neural networks
**Reading:** [*AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation*](https://files.sri.inf.ethz.ch/website/papers/sp2018.pdf)
**See also:** [*DL2: Training and Querying Neural Networks with Logic*](http://proceedings.mlr.press/v97/fischer19a/fischer19a.pdf) | --- | --- | MS2 Due +10/30 | Probabilistic programming languages
**Reading:** [*Probabilistic Programming*](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/fose-icse2014.pdf) | | | +11/2 | Verifying probabilistic programs
**Reading:** [*A Program Logic for Union Bounds*](https://arxiv.org/pdf/1602.05681)
**See also:** [*Advances and Challenges of Probabilistic Model Checking*](https://www.prismmodelchecker.org/papers/allerton10.pdf) | | | +11/4 | Languages for differential privacy
**Reading:** [*Distance Makes the Types Grow Stronger: A Calculus for Differential Privacy*](https://www.cis.upenn.edu/~bcpierce/papers/dp.pdf)
**See also:** [*Programming Language Techniques for Differential Privacy*](https://siglog.hosting.acm.org/wp-content/uploads/2016/01/siglog_news_7.pdf) | | | +11/6 | Verifying neural networks
**Reading:** [*AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation*](https://files.sri.inf.ethz.ch/website/papers/sp2018.pdf)
**See also:** [*DL2: Training and Querying Neural Networks with Logic*](http://proceedings.mlr.press/v97/fischer19a/fischer19a.pdf) | | | MS2 Due |

**No Lectures: Work on Projects**

| | | 12/7 |
**Project Presentations**
| | | 12/9 |
**Project Presentations**
| | |