[2023.01.05] Towards Deep Learning Models Resistant to Adversarial Attacks
작성자
smartm2m
작성일
2023-02-09 16:17
조회
625
AI 팀의 OJT 자료 #11
주제: Towards Deep Learning Models Resistant to Adversarial Attacks
1. Abstract
- Abstract
- Terms
2. Optimization view
- Formulation
- Unified view(Attack& Defense)
3. Universally Robustness
- Adversarial Training
- First-Order Adversaries
- Solved saddle point problem
4. Capacity & Robustness
- Adversarial Robustness
- Network Capacity
- Summary and Discussion
주제: Towards Deep Learning Models Resistant to Adversarial Attacks
1. Abstract
- Abstract
- Terms
2. Optimization view
- Formulation
- Unified view(Attack& Defense)
3. Universally Robustness
- Adversarial Training
- First-Order Adversaries
- Solved saddle point problem
4. Capacity & Robustness
- Adversarial Robustness
- Network Capacity
- Summary and Discussion
