MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples

Abstract

MagNet and "Efficient Defenses..." were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion.

References in corpus (1)

• APE-GAN: Adversarial Perturbation Elimination with GAN

Cited by in corpus (29)

• On Evaluating Adversarial Robustness
• Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
• Adversarial Examples in Modern Machine Learning: A Review
• Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis
• Mitigating Advanced Adversarial Attacks with More Advanced Gradient Obfuscation Techniques
• Adversarial Examples on Object Recognition: A Comprehensive Survey
• Enhancing Gradient-based Attacks with Symbolic Intervals
• Enhancing Certifiable Robustness via a Deep Model Ensemble
• Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks
• Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
• Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN
• Robustness Certificates Against Adversarial Examples for ReLU Networks
• Adversarial Robustness in Deep Learning: Attacks on Fragile Neurons
• Bandlimiting Neural Networks Against Adversarial Attacks
• Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders
• Adversarial Defense Through Network Profiling Based Path Extraction
• Minimax Defense against Gradient-based Adversarial Attacks
• AuxBlocks: Defense Adversarial Example via Auxiliary Blocks
• Detecting Adversarial Patches with Class Conditional Reconstruction Networks
• Attack as Defense: Characterizing Adversarial Examples using Robustness
• A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks
• Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?
• "What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models
• Who is Responsible for Adversarial Defense?
• TEAM: We Need More Powerful Adversarial Examples for DNNs
• Delving into the pixels of adversarial samples
• Attack to Fool and Explain Deep Networks
• Target Training Does Adversarial Training Without Adversarial Samples
• Tricking Adversarial Attacks To Fail