Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks

Abstract

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters. We apply ADMM (alternating direction method of multipliers) for solving the optimization problem of the fault sneaking attack with two constraints: 1) the classification of the other images should be unchanged and 2) the parameter modifications should be minimized. Specifically, the first constraint requires us not only to inject designated faults (misclassifications), but also to hide the faults for stealthy or sneaking considerations by maintaining model accuracy. The second constraint requires us to minimize the parameter modifications (using L0 norm to measure the number of modifications and L2 norm to measure the magnitude of modifications). Comprehensive experimental evaluation demonstrates that the proposed framework can inject multiple sneaking faults without losing the overall test accuracy performance.

Accepted by the 56th Design Automation Conference (DAC 2019)

References in corpus (13)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Poisoning Attacks against Support Vector Machines
• Robust Physical-World Attacks on Deep Learning Models
• Security Evaluation of Pattern Classifiers under Attack
• Efficient Neural Network Robustness Certification with General Activation Functions
• Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
• Is feature selection secure against training data poisoning?
• Randomized Prediction Games for Adversarial Machine Learning
• EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
• Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks
• Linearized ADMM for Non-convex Non-smooth Optimization with Convergence Analysis

Cited by in corpus (3)

• DeepDyve: Dynamic Verification for Deep Neural Networks
• FooBaR: Fault Fooling Backdoor Attack on Neural Network Training
• Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing System