Theoretical Foundations of Adversarially Robust Learning

• URL: http://arxiv.org/abs/2306.07723v1
• Date: Tue, 13 Jun 2023 12:20:55 GMT
• Title: Theoretical Foundations of Adversarially Robust Learning
• Authors: Omar Montasser
• Abstract summary: Current machine learning systems have been shown to be brittle against adversarial examples. In this thesis, we explore what robustness properties can we hope to guarantee against adversarial examples.
• Score: 7.589246500826111
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to misclassify. Can we learn predictors robust to adversarial examples? and how? There has been much empirical interest in this contemporary challenge in machine learning, and in this thesis, we address it from a theoretical perspective. In this thesis, we explore what robustness properties can we hope to guarantee against adversarial examples and develop an understanding of how to algorithmically guarantee them. We illustrate the need to go beyond traditional approaches and principles such as empirical risk minimization and uniform convergence, and make contributions that can be categorized as follows: (1) introducing problem formulations capturing aspects of emerging practical challenges in robust learning, (2) designing new learning algorithms with provable robustness guarantees, and (3) characterizing the complexity of robust learning and fundamental limitations on the performance of any algorithm.

Related papers

• Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data [38.44734564565478]
  We provide a theoretical understanding of adversarial examples and adversarial training algorithms from the perspective of feature learning theory. We show that the adversarial training method can provably strengthen the robust feature learning and suppress the non-robust feature learning.
  arXiv  Detail & Related papers  (2024-10-11T03:59:49Z)
• Fairness, Accuracy, and Unreliable Data [0.0]
  This thesis investigates three areas targeted at improving the reliability of machine learning; fairness in machine learning, strategic classification, and algorithmic robustness. A theme throughout this thesis is thinking about ways in which a plain' empirical risk minimization algorithm will be misleading or ineffective because of a mis-match between classical learning theory assumptions and specific properties of some data distribution in the wild.
  arXiv  Detail & Related papers  (2024-08-28T17:44:08Z)
• Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization [53.15874572081944]
  We study computability in the deep learning framework from two perspectives. We show algorithmic limitations in training deep neural networks even in cases where the underlying problem is well-behaved. Finally, we show that in quantized versions of classification and deep network training, computability restrictions do not arise or can be overcome to a certain degree.
  arXiv  Detail & Related papers  (2024-08-12T15:02:26Z)
• Rethinking Randomized Smoothing from the Perspective of Scalability [0.0]
  Randomized smoothing has emerged as a promising technique among notable advancements. We provide an in-depth exploration of the fundamental concepts underlying randomized smoothing. We highlight its theoretical guarantees in certifying robustness against adversarial perturbations.
  arXiv  Detail & Related papers  (2023-12-19T21:27:02Z)
• Resilient Constrained Learning [94.27081585149836]
  This paper presents a constrained learning approach that adapts the requirements while simultaneously solving the learning task. We call this approach resilient constrained learning after the term used to describe ecological systems that adapt to disruptions by modifying their operation.
  arXiv  Detail & Related papers  (2023-06-04T18:14:18Z)
• Understanding Self-Predictive Learning for Reinforcement Learning [61.62067048348786]
  We study the learning dynamics of self-predictive learning for reinforcement learning. We propose a novel self-predictive algorithm that learns two representations simultaneously.
  arXiv  Detail & Related papers  (2022-12-06T20:43:37Z)
• Adversarial Robustness with Semi-Infinite Constrained Learning [177.42714838799924]
  Deep learning to inputs perturbations has raised serious questions about its use in safety-critical domains. We propose a hybrid Langevin Monte Carlo training approach to mitigate this issue. We show that our approach can mitigate the trade-off between state-of-the-art performance and robust robustness.
  arXiv  Detail & Related papers  (2021-10-29T13:30:42Z)
• Quantifying Epistemic Uncertainty in Deep Learning [15.494774321257939]
  Uncertainty quantification is at the core of the reliability and robustness of machine learning. We provide a theoretical framework to dissect the uncertainty, especially the textitepistemic component, in deep learning. We propose two approaches to estimate these uncertainties, one based on influence function and one on variability.
  arXiv  Detail & Related papers  (2021-10-23T03:21:10Z)
• When and How to Fool Explainable Models (and Humans) with Adversarial Examples [1.439518478021091]
  We explore the possibilities and limits of adversarial attacks for explainable machine learning models. First, we extend the notion of adversarial examples to fit in explainable machine learning scenarios. Next, we propose a comprehensive framework to study whether adversarial examples can be generated for explainable models.
  arXiv  Detail & Related papers  (2021-07-05T11:20:55Z)
• Constrained Learning with Non-Convex Losses [119.8736858597118]
  Though learning has become a core technology of modern information processing, there is now ample evidence that it can lead to biased, unsafe, and prejudiced solutions.
  arXiv  Detail & Related papers  (2021-03-08T23:10:33Z)
• Probably Approximately Correct Constrained Learning [135.48447120228658]
  We develop a generalization theory based on the probably approximately correct (PAC) learning framework. We show that imposing a learner does not make a learning problem harder in the sense that any PAC learnable class is also a constrained learner. We analyze the properties of this solution and use it to illustrate how constrained learning can address problems in fair and robust classification.
  arXiv  Detail & Related papers  (2020-06-09T19:59:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.