Robusta: Robust AutoML for Feature Selection via Reinforcement Learning

Abstract

Several AutoML approaches have been proposed to automate the machine learning (ML) process, such as searching for the ML model architectures and hyper-parameters. However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks. As ML systems are increasingly being used in a variety of mission-critical applications, improving the robustness of ML systems has become of utmost importance. In this paper, we propose the first robust AutoML framework, Robusta--based on reinforcement learning (RL)--to perform feature selection, aiming to select features that lead to both accurate and robust ML systems. We show that a variation of the 0-1 robust loss can be directly optimized via an RL-based combinatorial search in the feature selection scenario. In addition, we employ heuristics to accelerate the search procedure based on feature scoring metrics, which are mutual information scores, tree-based classifiers feature importance scores, F scores, and Integrated Gradient (IG) scores, as well as their combinations. We conduct extensive experiments and show that the proposed framework is able to improve the model robustness by up to 22% while maintaining competitive accuracy on benign samples compared with other feature selection methods.

References in corpus (12)

• Playing Atari with Deep Reinforcement Learning
• Axiomatic Attribution for Deep Networks
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Theoretically Principled Trade-off between Robustness and Accuracy
• Robustness May Be at Odds with Accuracy
• Towards Fast Computation of Certified Robustness for ReLU Networks
• Adversarial Examples Are a Natural Consequence of Test Error in Noise
• MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius
• Feature Engineering for Predictive Modeling using Reinforcement Learning
• Lipschitz regularized Deep Neural Networks generalize and are adversarially robust
• Defense Against the Dark Arts: An overview of adversarial example security research and future research directions
• Robust binary classification with the 01 loss