Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples
arXiv:1705.10686
Abstract
Feature squeezing is a recently-introduced framework for mitigating and detecting adversarial examples. In previous work, we showed that it is effective against several earlier methods for generating adversarial examples. In this short note, we report on recent results showing that simple feature squeezing techniques also make deep learning models significantly more robust against the Carlini/Wagner attacks, which are the best known adversarial methods discovered to date.
References in corpus (1)
Cited by in corpus (17)
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
- Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong
- Adversarial Perturbations Against Real-Time Video Classification Systems
- Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight
- The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning
- Randomization matters. How to defend against strong adversarial attacks
- Security and Privacy for Artificial Intelligence: Opportunities and Challenges
- Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things
- Moving Target Defense for Deep Visual Sensing against Adversarial Examples
- Clipping free attacks against artificial neural networks
- Recovery Guarantees for Compressible Signals with Adversarial Noise
- On Lyapunov exponents and adversarial perturbation
- Resilience from Diversity: Population-based approach to harden models against adversarial attacks
- Decoder-free Robustness Disentanglement without (Additional) Supervision