DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

Abstract

Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attacks can severely undermine DNN systems, particularly in security-sensitive settings. It was observed that an adversary could easily generate adversarial samples by making a small perturbation on irrelevant feature dimensions that are unnecessary for the current classification task. To overcome this problem, we introduce a defensive mechanism called DeepCloak. By identifying and removing unnecessary features in a DNN model, DeepCloak limits the capacity an attacker can use generating adversarial samples and therefore increase the robustness against such inputs. Comparing with other defensive approaches, DeepCloak is easy to implement and computationally efficient. Experimental results show that DeepCloak can increase the performance of state-of-the-art DNN models against adversarial samples.

adversarial samples, deep neural network

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Wide Residual Networks

Cited by in corpus (20)

• Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
• Microsoft Malware Classification Challenge
• Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
• Adversarial Examples - A Complete Characterisation of the Phenomenon
• Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review
• Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective
• The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey
• Improving adversarial robustness of deep neural networks by using semantic information
• Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding
• Adversarial Examples on Object Recognition: A Comprehensive Survey
• Generative Dynamic Patch Attack
• Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN
• Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
• Weight Map Layer for Noise and Adversarial Attack Robustness
• DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning
• FineFool: Fine Object Contour Attack via Attention
• A Unified Game-Theoretic Interpretation of Adversarial Robustness
• Orthogonal Deep Models As Defense Against Black-Box Attacks