AntTech
Oct 31, 2022 · Artificial Intelligence
Automated Attacker A² for Enhancing Model Robustness in Adversarial Training
The paper presents A², an automated, parameterized attacker that dynamically adjusts perturbation methods and step sizes during adversarial training, demonstrating improved robustness across multiple benchmarks with modest computational overhead, and outlines future directions for further efficiency and effectiveness in secure AI systems.
NeurIPSadversarial trainingautomated attacker
0 likes · 9 min read