Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization — mentioned by nl

Thu, 03 Nov 2016 10:28:45 GMT

https://arxiv.org/abs/1412.6572 is a Goodfellow et. al. (ie, the person who's Tweet you note above) paper where they show adversarial examples do apply across architectures (as you state above), but they show that using the adversarial examples during training has a regularization effect and improves performance: https://arxiv.org/pdf/1511.05432v3.pdf takes a similar approach: We show that adversarial training of ANNs is in fact robustification of the network optimization, and that our proposed framework generalizes previous approaches for increasing local stability of ANNs. Experimental…

Paper and discussion history. A mention is not an endorsement.

Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization · HackerPapers discussions

Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization — mentioned by nl