Improving Certified Robustness via Statistical Learning with Logical Reasoning

Abstract

Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification methods are only able to certify under a limited perturbation radius. Given that existing pure data-driven statistical approaches have reached a bottleneck, in this paper, we propose to integrate statistical ML models with knowledge (expressed as logical rules) as a reasoning component using Markov logic networks (MLN, so as to further improve the overall certified robustness. This opens new research questions about certifying the robustness of such a paradigm, especially the reasoning component (e.g., MLN). As the first step towards understanding these questions, we first prove that the computational complexity of certifying the robustness of MLN is #P-hard. Guided by this hardness result, we then derive the first certified robustness bound for MLN by carefully analyzing different model regimes. Finally, we conduct extensive experiments on five datasets including both high-dimensional images and natural language texts, and we show that the certified robustness with knowledge-based logical reasoning indeed significantly outperforms that of the state-of-the-arts.

arXiv commentAccepted by 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

References in corpus (17)

• Ensemble Adversarial Training: Attacks and Defenses
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Delving into Transferable Adversarial Examples and Black-box Attacks
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Certified Adversarial Robustness via Randomized Smoothing
• Robustness May Be at Odds with Accuracy
• Efficient Neural Network Robustness Certification with General Activation Functions
• Evaluating Robustness of Neural Networks with Mixed Integer Programming
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
• Generating Adversarial Examples with Adversarial Networks
• Improving Adversarial Robustness via Promoting Ensemble Diversity
• Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
• Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness
• Joint Inference of Reward Machines and Policies for Reinforcement Learning
• Enhancing Certified Robustness via Smoothed Weighted Ensembling

Cited by in corpus (4)

• Software Engineering for AI-Based Systems: A Survey
• RAB: Provable Robustness Against Backdoor Attacks
• Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
• QiaoNing at SemEval-2020 Task 4: Commonsense Validation and Explanation system based on ensemble of language model