[Paper Reading] Adversarial training descends without descent: Finding actual descent directions based on Danskin’s Theorem
🗓
👀 
For mobile: View PDF
Main References
- Fabian Latorre, Igor Krawczuk, Leello Tadesse Dadi, Thomas Pethick, and Volkan Cevher. Finding Actual Descent Directions for Adversarial Training. ICLR 2023.
- Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu Towards Deep Learning Models Resistant to Adversarial Attacks. ICLR 2018.