09:40 〜 10:00
[2K1-ES-2-03] Is Neural Architecture Search A Way Forward to Develop Robust Neural Networks?
キーワード：Deep Learning, Neuro-Evolution, Evolutionary Strategies, Adversarial Machine Learning
An imperceptibly altered image can mislead nearly all neural networks to predict inaccurately.
These modified images are also known as adversarial examples are generated by a special class of algorithms known as adversarial attacks.
Many defensive algorithms are proposed to prevent the neural networks from such attacks, but none have satisfying outcomes.
Recently, an innovative algorithm is proposed which claims to evolve intrinsically robust neural networks using neural architecture search.
Previously, neural architecture searches have been used in the development of many accurate state-of-the-art neural networks.
We examine this new algorithm to understand the feasibility of such architecture search in the domain of adversarial machine learning.
Thus, we illustrate that more robust architectures exist as well as open up a new realm of possibilities for the advancement and exploration of neural networks using neural architecture search.
These modified images are also known as adversarial examples are generated by a special class of algorithms known as adversarial attacks.
Many defensive algorithms are proposed to prevent the neural networks from such attacks, but none have satisfying outcomes.
Recently, an innovative algorithm is proposed which claims to evolve intrinsically robust neural networks using neural architecture search.
Previously, neural architecture searches have been used in the development of many accurate state-of-the-art neural networks.
We examine this new algorithm to understand the feasibility of such architecture search in the domain of adversarial machine learning.
Thus, we illustrate that more robust architectures exist as well as open up a new realm of possibilities for the advancement and exploration of neural networks using neural architecture search.
講演PDFパスワード認証
論文PDFの閲覧にはログインが必要です。参加登録者の方は「参加者用ログイン」画面からログインしてください。あるいは論文PDF閲覧用のパスワードを以下にご入力ください。