Attacks Against Machine Learning Models

Attacks Against Machine Learning Models

 

Overview

---

This course will cover the topic of attacks against machine learning models

• Privacy
  • Membership inference
  • Dataset reconstruction
  • Attribute inference
• Security
  • Backdoor
  • Model stealing
• Safety
  • Hijacking
  • Toxicity

Prerequisites

---

• Basic knowledge of machine learning and data mining
• A security background is not needed

 

Logistics

---

Location: Lecture hall, CISPA Building, E9 1

Lecturer: Yang Zhang

Assistants: 

Contact: 

Time: Monday 14:00 - 15:30

Contact: 

 

Schedule

---

4.29 Yang Zhang (Membership inference)
5.6 Zheng Li (Membership inference)
5.13 Rui Wen (Data reconstruction + model stealing)
5.27 Boyang Zhang (Plot + SecurityNet)
6.3 Yugeng Liu (Backdoor + Poisoning)
6.10 Mingjie Li (Adversarial Example)
6.17 Yiting Qu (Safety of VLM)
6.24 Zeyang Sha (Deepfake Detection)
7.1 Wai Man Si (Safety + Hijacking)
7.8 Xinyue Shen (Prompt stealing + Jailbreak)

Grading

---

The course will be graded by 100% via oral exam. 

Note that students who have taken the advanced lectures

- Machine Learning Privacy

- Privacy Enhancing Technologies (2018-2021) 

cannot take this one due to the significant overlap between them.