深層学習はロボットビジョンにとって安全か?iCubヒューマノイドに対する敵対的サンプル
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid
iCubヒューマノイドの視覚システムに組み込まれた深層学習が敵対的サンプルにどの程度脆弱かを評価し、異常入力の分類を拒否する計算効率の良い対策を提案した。
著者: Marco Melis, Ambra Demontis, Battista Biggio, Gavin Brown, Giorgio Fumera, Fabio Roli
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
Deep neural networks have been widely adopted in recent years, exhibiting impressive performances in several application domains. It has however been shown that they can be fooled by adversarial examples, i.e., images altered by a barely-perceivable adversarial noise, carefully crafted to mislead classification. In this work, we aim to evaluate the extent to which robot-vision systems embodying deep-learning algorithms are vulnerable to adversarial examples, and propose a computationally efficient countermeasure to mitigate this threat, based on rejecting classification of anomalous inputs. We then provide a clearer understanding of the safety properties of deep networks through an intuitive empirical analysis, showing that the mapping learned by such networks essentially violates the smoothness assumption of learning algorithms. We finally discuss the main limitations of this work, including the creation of real-world adversarial examples, and sketch promising research directions.
