cs763/website/docs/schedule/lectures.md

Calendar (Tentative)

For differential privacy, we will use the textbook Algorithmic Foundations of Data Privacy (AFDP) by Cynthia Dwork and Aaron Roth, available here.

Date	Topic	Presenter
Differential Privacy
9/5	Course welcome, introducing differential privacy Paper: Keshav. How to Read a Paper.	JH
9/10	Basic private mechanisms Reading: AFDP 3.2, 3.3	JH
9/12	Composition and closure properties Reading: AFDP 3.5	JH
9/17	What does differential privacy actually mean? Reading: McSherry. Lunchtime for Differential Privacy (see also these two posts)	JH
9/19	Exponential mechanism Paper: McSherry and Talwar. Mechanism Design via Differential Privacy. Due: Project topics and groups	JH
9/21 (FRI)	Identity-Based Encryption from the Diffie-Hellman Assumption SPECIAL TIME AND PLACE: 4 PM, CS 1240	Sanjam Garg
9/24	Report-noisy-max and the Sparse Vector Technique Reading: AFDP 3.3, 3.5	JH
9/26	Privacy for data streams Paper: Chan, Shi, and Song. Private and Continual Release of Statistics.	Yinglun
10/1	Local differential privacy Paper: Erlingsson, Pihur, and Korolova. RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response.	JH
Adversarial Machine Learning
10/3	AML: overview and basics GUEST LECTURE	Somesh Jha
10/8	History of Adversarial ML Paper: Biggio and Roli. Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning.	Meghana
10/10	Adversarial examples Paper: Szegedy, Zaremba, Sutskever, et al. Intriguing Properties of Neural Networks.	Shimaa
10/15	NO CLASS: INSTRUCTOR AWAY
10/17	NO CLASS: INSTRUCTOR AWAY Due: Milestone 1
10/22	Adversarial examples Paper: Goodfellow, Schlens, and Szegedy. Explaining and Harnessing Adversarial Examples.	Kyrie
10/24	Real-world attacks Paper: Eykholt, Evtimov, Fernandes, et al. Robust Physical-World Attacks on Deep Learning Models.	Hiba
10/29	Detection methods Paper: Carlini and Wagner. Towards Evaluating the Robustness of Neural Networks.	Yiqin
10/31	Detection methods Paper: Carlini and Wagner. Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods.	Junxiong
11/5	Defensive measures Paper: Steinhardt, Koh, and Liang. Certified Defenses for Data Poisoning Attacks.	Yaman
11/7	Defensive measures Paper: Madry, Makelov, Schmidt, Schmidt, Tsipras, and Valdu. Towards Deep Learning Models Resistant to Adversarial Attacks.	Maddy
Cryptographic Techniques
11/12	Applied crypto: overview and basics	JH
11/14	Verifiable computing Paper: Braun, Feldman, Ren, et al. Verifying Computations with State. Due: Milestone 2	Kan
11/19	Verifiable differential privacy Paper: Narayan, Feldman, Papadimitriou, and Haeberlen. Verifiable Differential Privacy.	Fayi
11/21	Homomorphic encryption Paper: Ducas and Micciancio. FHEW: Bootstrapping Homomorphic Encryption in Less than a Second.	Yue
Language-Based Security
11/26	Language-based security: overview and basics	JH
11/28	Languages for privacy Paper: Reed and Pierce. Distance Makes the Types Grow Stronger: A Calculus for Differential Privacy.	Sam
12/3	Languages for authenticated datastructures Paper: Miller, Hicks, Katz, and Shi. Authenticated Data Structures, Generically.	Zichuan
12/5	Languages for oblivous computing Paper: Zahur and Evans. Obliv-C: A Language for Extensible Data-Oblivious Computation.	Zhiyi
12/10	Languages for information flow Paper: Griffin, Levy, Stefan, et al. Hails: Protecting Data Privacy in Untrusted Web Applications.	Arjun
12/12	Languages for preventing timing channels Paper: Zhang, Askarov, and Myers. Language-Based Control and Mitigation of Timing Channels.	Yan