Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We develop a notion of representation vulnerability that captures the maximum change of mutual information between the input and output distributions, under the worst-case input perturbation. Then, we prove a theorem that establishes a lower bound on the minimum adversarial risk that can be achieved for any downstream classifier based on its representation vulnerability. We propose an unsupervised learning method for obtaining intrinsically robust representations by maximizing the worst-case mutual information between the input and output distributions. Experiments on downstream classification tasks support the robustness of the representations found using unsupervised learning with our training principle.
Code (2)
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
On Proper Learnability between Average- and Worst-case Robustness
Recently, Montasser et al. [2019] showed that finite VC dimension is not sufficient for proper adversarially robust PAC learning. In light of this hardness, there is a growing effort to study what type of relaxations to …
PAC learningLearning Discrete Structured Representations by Adversarially Maximizing Mutual Information
We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable i…
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world distribution shifts (e.…
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
In multi-agent reinforcement learning (MARL), ensuring robustness against unpredictable or worst-case actions by allies is crucial for real-world deployment. Existing robust MARL methods either approximate or enumerate a…
Multi-agent Reinforcement LearningOff-policy evaluationreinforcement-learningReinforcement Learning+2Learning deep representations by mutual information estimation and maximization
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporat…
General ClassificationMutual Information EstimationRepresentation Learning