Weekly Schedule

The schedule along with the list of topics to be covered are tentative and subject to change.

Week		Date	Module	Topic	Reading	Assignment
1	T	8/25	Introduction	How AI fails, and what “trust” decomposes into (slides)		Post a note on Teams to introduce yourself. Review the Syllabus.
	R	8/27	Introduction	Convolutional networks and transformers (notebook)	Phuong & Hutter, Formal Algorithms for Transformers	Setup software and development environment for the course (see here) Assignment 0 out
2	T	9/1		No class: Ravi traveling
	R	9/3		No class: Ravi traveling
3	T	9/8	Introduction	Transformer review and post-training (notebook)	Rafailov et al., Direct Preference Optimization (§3-4)
	R	9/10	Robustness Attacks	Adversarial examples as constrained optimization (notebook)	Goodfellow et al., Explaining and Harnessing Adversarial Examples; Madry et al., Towards Deep Learning Models Resistant to Adversarial Attacks (§2); Gilmer et al., Motivating the Rules of the Game for Adversarial Example Research
4	T	9/15	Robustness Attacks	Jailbreaking: GCG as discrete PGD (notebook)	Zou et al., Universal and Transferable Adversarial Attacks on Aligned Language Models	Assignment 0 due Assignment 1 out
	R	9/17	Robustness Defenses	Empirical defenses, on images and on language models (notebook)	Madry et al., Towards Deep Learning Models Resistant to Adversarial Attacks; Sharma et al., Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
5	T	9/22	Robustness Defenses	Empirical defenses, continued: evaluating a defense (notebook)	Athalye et al., Obfuscated Gradients Give a False Sense of Security; Carlini et al., On Evaluating Adversarial Robustness (§2-3)
	R	9/24	Robustness Guarantees	Certified robustness: bound propagation (notebook)	Gowal et al., On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models; Singh et al., An Abstract Domain for Certifying Neural Networks (skim)
6	T	9/29	Robustness Guarantees Interpretability	Certified robustness, continued (notebook) Input attribution (notebook)	Sundararajan et al., Axiomatic Attribution for Deep Networks	Assignment 1 due Assignment 2 out
	R	10/1	Interpretability	Input attribution and its weaknesses, continued (notebook)	Adebayo et al., Sanity Checks for Saliency Maps
7	T	10/6		No class: Ravi traveling
	R	10/8	Interpretability	Probes, concepts, and steering
8	T	10/13	Interpretability	Circuits and sparse autoencoders
	R	10/15		Review and catch-up		Assignment 2 due
9	T	10/20		Midterm
	R	10/22	Training-time Failures	Data poisoning and backdoors		Assignment 3 out
10	T	10/27	Training-time Failures	Sleeper agents and emergent misalignment
	R	10/29	Training-time Failures	Reward hacking and specification gaming
11	T	11/3	Calibration and Evaluation	Does the model know when it is wrong?		Project proposal due
	R	11/5	Calibration and Evaluation	Benchmarks, red teams, and judges
12	T	11/10		Guest lecture: Provenance and watermarking
	R	11/12	Agents	Agent architecture and the agent threat model
13	T	11/17	Agents	Prompt injection		Assignment 3 due Assignment 4 out
	R	11/19	Agents	Structural defenses
14	T	11/24		No class: Fall recess
	R	11/26		No class: Fall recess
15	T	12/1	Agents	Runtime oversight		Assignment 4 due 12/5
	R	12/3		No class: Ravi traveling
16	T	12/8	Wrap-up	Project presentations
	R	12/10	Wrap-up	What we did not cover		Project report due
Finals	W	12/16		Final Exam in CSB 130 (6:20-8:20 pm)