Timezone: »

 
Poster
Phase Transition from Clean Training to Adversarial Training
Yue Xing · Qifan Song · Guang Cheng

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #206

Adversarial training is one important algorithm to achieve robust machine learning models. However, numerous empirical results show a great performance degradation from clean training to adversarial training (e.g., 90+\% vs 67\% testing accuracy on CIFAR-10 dataset), which does not match the theoretical guarantee delivered by the existing studies. Such a gap inspires us to explore the existence of an (asymptotic) phase transition phenomenon with respect to the attack strength: adversarial training is as well behaved as clean training in the small-attack regime, but there is a sharp transition from clean training to adversarial training in the large-attack regime. We validate this conjecture in linear regression models, and conduct comprehensive experiments in deep neural networks.

Author Information

Yue Xing (Purdue University)
Qifan Song (Purdue University )
Guang Cheng (University of California, Los Angeles)

More from the Same Authors