spml2025

Security and Privacy in Machine Learning Sharif University of Technology, Iran CE Department Fall 2025

   

Welcome to the public page for the course on Security and Privacy in Machine Learning (SPML). The main objectives of the course are to introduce students to the principles of security and privacy in machine learning. The students become familiar with the vulnerabilities of machine learning in the training and inference phases and the methods to improve the robustness and privacy of machine learning models.

Course Logistics

• Time: Saturday & Monday: 10:30 – 12:00
• Location: Room 103 & vc.sharif.edu/ch/amsadeghzadeh
• Contact: Announcements and all course-related questions will happen on the Quera forum. * All official announcements and communication will happen over Telegram channel.
  • For external enquiries, emergencies, or personal matters that you don’t wish to put in a private post, you can email me at sadeghzadeh_at_sharif_dot_edu

Instructor

   Amir Mahdi Sadeghzadeh
   Office: CE-704    Lab: CE-502    Office Hours: By appointment (through Email)
   Email: amsadeghzadeh_at_gmail.com
   URL: amsadeghzadeh.github.io

Course Staff

• Arian Komaei Koma (Head Course Assistant) - Email: ariankomaei_at_gmail.com
• Alireza Faraj Tabrizi (Head Course Assistant) - Email: Alireza15farajtabrizi_at_gmail.com
• Amir Ezzati (Head Course Assistant) - Email: iamirezzati_at_gmail.com
• Firoozeh Abrishami (Course Assistant) - Email: f.abrishami110_at_gmail.com
• Ramtin moslemi (Course Assistant) - Email: ramtin4moslemi_at_gmail.com
• Erfan Sobhaei (Course Assistant) - Email: E.sobhaei_at_gmail.com

Course Pages

• spml2025.github.io -> Course information, syllabus, and materials.
• Course Telgram Channel
• Quera (Get the password from course staff) -> Announcements, assignments, and all course-related questions.
• Course Telegram Group -> Contact the Head Teaching Assistant for student confirmation and group inclusion.

Main References

The main references for the course are many research papers in top-tier conferences and journals in computer security (SP, CCS, Usenix Security, EuroSP) and machine learning (NeurIPS, ICLR, ICML, CVPR, ECCV). Three following books are used for presenting background topics in machine learning and deep learning in the first part of the course.

• Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.

• Ian Goodfellow, Deep Learning, MIT Press, 2016.

• Aston Zhang, Dive into Deep Learning, 2020

Grading Policy

• Assignments (30%)

• 4 Quizzes (10%)

• Presentation (10%)

• Mid-term (20%)

• Final (30%).

Course Policy

• This course considers topics involving personal and public privacy and security. As part of this investigation we will cover technologies whose abuse may infringe on the rights of others. As an instructor, I rely on the ethical use of these technologies. Unethical use may include circumvention of existing security or privacy measurements for any purpose, or the dissemination, promotion, or exploitation of vulnerabilities of these services. Exceptions to these guidelines may occur in the process of reporting vulnerabilities through public and authoritative channels. Any activity outside the letter or spirit of these guidelines will be reported to the proper authorities and may result in dismissal from the class. When in doubt, please contact the instructor for advice. Do not undertake any action which could be perceived as technology misuse anywhere and/or under any circumstances unless you have received explicit permission from Dr. Sadeghzadeh.

Academic Honesty

Sharif CE Department Honor Code (please read it carefully!)

Homework Submission

Submit your answers in .pdf or .zip file in course page on Quera website, with the following format: HW[HW#]-[FamilyName]-[std#] (For example HW3-Hoseini-401234567)

Homework Policy

Important:

• All theory homework must be handwritten.
• Do not submit LaTeX or Word-formatted documents for theory assignments — these will not be accepted.
• If any part of your homework is detected to be written by AI, you will receive no score for that assignment.
• You may use AI tools for assistance (e.g., brainstorming ideas, clarifying concepts, or debugging), but you must not include AI-generated text directly in your submission. All submitted work should be written in your own words and understanding.

Late Policy

• All students have 15 free late days for the assignments.
• You may use up to 4 late days per assignment with no penalty.
• Once you have exhausted your free late days, we will deduct a late penalty of 20% per additional late day.

   

   

#	Date	Topic	Content	Lecture	Reading	HWs	Quiz
1	7/19	Course Intro.	The scope and contents of the course	Lec1	Towards the Science of Security and Privacy in Machine Learning
2	7/21	Deep Learning Review	ML Intro., Perceptron, Logistic regression, GD, Regularization	Lec2	Pattern Recognition and Machine Learning Ch.1 & Ch.4 Deep Learning Ch.5 & Ch.6	HW0
3	7/26	Adversarial Examples	Properties of neural networks, Adversarial Example (L-BFGS), Type of Adversarial Attacks	Lec3	Intriguing Properties of Neural Networks
4	7/28	Adversarial Examples	Fast Gradient Sign Method(FGSM) Attack, L_P Norms	Lec4	Explaining and Harnessing Adversarial Examples
5	8/3	Adversarial Examples	C&W Attack	Lec5	Towards Evaluating the Robustness of Neural Networks
6	8/5	Adversarial Examples	Projected Gradient Descent, Universal Adversarial Perturbations, Adversarial Patch	Lec6	Universal Adversarial Perturbations Adversarial Patch		Quiz1
7	8/10	Adversarial Examples	Obfuscated Gradients, Adversarial Training, TRADES	Lec7	Theoretically Principled Trade-off between Robustness and Accuracy Mitigating Adversarial Effects Through Randomization Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
8	8/12	Adversarial Examples	Certifiable Robustness, Randomized Smoothing	Lec8	Certified Adversarial Robustness via Randomized Smoothing
9	8/17	AE		Lec9
10	8/19	-		-
11	8/24	AE		Lec10
12	8/26	Black box		Lec11			Quiz2
13	9/1	Poisoning		Lec12
14	9/8	Poisoning		Lec13
15	9/10	Model extraction		Lec14
16	9/15	MIA		Lec15
17	9/17	DP		Lec16
Exam	9/20 9AM	Midterm
18	9/22	DP		Lec17			Quiz3
19	9/24	DP		Lec18
20	9/29	Intro to LLM and challenges		Lec19
21	10/1	Hallucination		Lec20
22	10/6	Alignment(RLHF-DPO)		Lec21
23	10/8	Jailbreak of llm		Lec22
24	10/15	Jailbreak of vlm		Lec23			Quiz4
25	10/20	-		Lec24
26	10/22	-		Lec25
Exam	11/4	Final

This site is open source. Improve this page.