paper-with-me

Papers

On Achieving Optimal Adversarial Test Error

2023-06-13 · Justin D. Li, Matus Telgarsky

We first elucidate various fundamental properties of optimal adversarial predictors: the structure of optimal adversarial convex predictors in terms of optimal adversarial zero-one predictors, bounds relating the adversarial convex loss to the adversarial zero-one loss, and the fact that continuous predictors can get arbitrarily close to the optimal adversarial error for both convex and zero-one losses. Applying these results along with new Rademacher complexity bounds for adversarial training near initialization, we prove that for general data distributions and perturbation sets, adversarial training on shallow networks with early stopping and an idealized optimal adversary is able to achieve optimal adversarial test error. By contrast, prior theoretical work either considered specialized data distributions or only provided training error guarantees.

📄 PDF Abstract BibTeX arXiv:2306.07544

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy

2019-06-16 · Alex Lamb, Vikas Verma, Kenji Kawaguchi, Alexander Matyasko 외

Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt genera…

Adversarial Robustness

Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error

2025-02-23 · Haoran Li, ZiCheng Zhang, Wang Luo, Congying Han 외

Ensuring the robustness of deep reinforcement learning (DRL) agents against adversarial attacks is critical for their trustworthy deployment. Recent research highlights the challenges of achieving state-adversarial robus…

Adversarial RobustnessDeep Reinforcement Learningreinforcement-learningReinforcement Learning

Classifier-independent Lower-Bounds for Adversarial Robustness

2020-06-17 · Elvis Dohmatob

We theoretically analyse the limits of robustness to test-time adversarial and noisy examples in classification. Our work focuses on deriving bounds which uniformly apply to all classifiers (i.e all measurable functions …

Adversarial AttackAdversarial RobustnessGeneral Classification

Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits

2023-09-02 · NeurIPS 2023 11

We consider the adversarial linear contextual bandit problem, where the loss vectors are selected fully adversarially and the per-round action set (i.e. the context) is drawn from a fixed distribution. Existing methods f…

Computational EfficiencyMulti-Armed Bandits

Adversarial Question Answering Robustness: A Multi-Level Error Analysis and Mitigation Study

2026-01-06 · Agniv Roy Choudhury, Vignesh Ponselvan Rajasingh arxiv

Question answering (QA) systems achieve impressive performance on standard benchmarks like SQuAD, but remain vulnerable to adversarial examples. This project investigates the adversarial robustness of transformer models …

Adversarial RobustnessContrastive LearningQuestion AnsweringData Augmentation