Morphence: Moving Target Defense Against Adversarial Examples

Abstract

Robustness to adversarial examples of machine learning models remains an open topic of research. Attacks often succeed by repeatedly probing a fixed target model with adversarial examples purposely crafted to fool it. In this paper, we introduce Morphence, an approach that shifts the defense landscape by making a model a moving target against adversarial examples. By regularly moving the decision function of a model, Morphence makes it significantly challenging for repeated or correlated attacks to succeed. Morphence deploys a pool of models generated from a base model in a manner that introduces sufficient randomness when it responds to prediction queries. To ensure repeated or correlated attacks fail, the deployed pool of models automatically expires after a query budget is reached and the model pool is seamlessly replaced by a new model pool generated in advance. We evaluate Morphence on two benchmark image classification datasets (MNIST and CIFAR10) against five reference attacks (2 white-box and 3 black-box). In all cases, Morphence consistently outperforms the thus-far effective defense, adversarial training, even in the face of strong white-box attacks, while preserving accuracy on clean data.

References in corpus (19)

• Explaining and Harnessing Adversarial Examples
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Evasion Attacks against Machine Learning at Test Time
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Certified Adversarial Robustness via Randomized Smoothing
• On Evaluating Adversarial Robustness
• Certified Defenses against Adversarial Examples
• Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
• Learning with a Strong Adversary
• Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
• Certified Adversarial Robustness with Additive Noise
• Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data
• Foveation-based Mechanisms Alleviate Adversarial Examples
• A Research Agenda: Dynamic Models to Defend Against Correlated Attacks
• EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attacks