Adversarial attacks hidden in plain sight

Abstract

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into making any desired incorrect classification, potentially with very high certainty. Several defensive approaches increase robustness against adversarial attacks, demanding attacks of greater magnitude, which lead to visible artifacts. By considering human visual perception, we compose a technique that allows to hide such adversarial attacks in regions of high complexity, such that they are imperceptible even to an astute observer. We carry out a user study on classifying adversarially modified images to validate the perceptual quality of our approach and find significant evidence for its concealment with regards to human visual perception.

References in corpus (6)

• Explaining and Harnessing Adversarial Examples
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Parseval Networks: Improving Robustness to Adversarial Examples
• Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
• Detecting Adversarial Examples through Nonlinear Dimensionality Reduction

Cited by in corpus (2)

• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Kryptonite: An Adversarial Attack Using Regional Focus