Discretization based Solutions for Secure Machine Learning against Adversarial Attacks
Adversarial examples are perturbed inputs that are designed (from a deep learning network's (DLN) parameter gradients) to mislead the DLN during test time. Intuitively, constraining the dimensionality of inputs or parameters of a network reduces the 'space' in which adversarial examples exist. Guided by this intuition, we demonstrate that discretization greatly improves the robustness of DLNs against adversarial attacks. Specifically, discretizing the input space (or allowed pixel levels from 256 values or 8-bit to 4 values or 2-bit) extensively improves the adversarial robustness of DLNs for a substantial range of perturbations for minimal loss in test accuracy. Furthermore, we find that Binary Neural Networks (BNNs) and related variants are intrinsically more robust than their full precision counterparts in adversarial scenarios. Combining input discretization with BNNs furthers the robustness even waiving the need for adversarial training for certain magnitude of perturbation values. We evaluate the effect of discretization on MNIST, CIFAR10, CIFAR100 and Imagenet datasets. Across all datasets, we observe maximal adversarial resistance with 2-bit input discretization that incurs an adversarial accuracy loss of just ~1-2% as compared to clean test accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessBIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Discretization-based ensemble model for robust learning in IoT
IoT device identification is the process of recognizing and verifying connected IoT devices to the network. This is an essential process for ensuring that only authorized devices can access the network, and it is necessa…
IoT Device IdentificationManagementTowards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly …
Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods
Deep neural networks have achieved state-of-the-art performance in a variety of fields. Recent works observe that a class of widely used neural networks can be viewed as the Euler method of numerical discretization. From…
FedDiscrete: A Secure Federated Learning Algorithm Against Weight Poisoning
Federated learning (FL) is a privacy-aware collaborative learning paradigm that allows multiple parties to jointly train a machine learning model without sharing their private data. However, recent studies have shown tha…
Federated Learningsecml: A Python Library for Secure and Explainable Machine Learning
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adver…
BIG-bench Machine Learning