paper-with-me

Papers

Provably Minimally-Distorted Adversarial Examples

2017-09-29 · Nicholas Carlini, Guy Katz, Clark Barrett, David L. Dill

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques have been proposed for increasing robustness to adversarial examples --- and yet most of these have been quickly shown to be vulnerable to future attacks. For example, over half of the defenses proposed by papers accepted at ICLR 2018 have already been broken. We propose to address this difficulty through formal verification techniques. We show how to construct provably minimally distorted adversarial examples: given an arbitrary neural network and input sample, we can construct adversarial examples which we prove are of minimal distortion. Using this approach, we demonstrate that one of the recent ICLR defense proposals, adversarial retraining, provably succeeds at increasing the distortion required to construct adversarial examples by a factor of 4.2.

📄 PDF Abstract BibTeX arXiv:1709.10207

Code (1)

huanzhang12/ATLA_robust_RL pytorch

Similar Papers 제목 키워드 기반

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack

2019-07-03 · ICML 2020 1 · Francesco Croce, Matthias Hein

The evaluation of robustness against adversarial manipulation of neural networks-based classifiers is mainly tested with empirical attacks as methods for the exact computation, even when available, do not scale to large …

Adversarial Attack

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

2024-04-11 · NeurIPS 2023 11 · Runqi Lin, Chaojian Yu, Tongliang Liu

Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenomenon that leads to a severely distorted …

Adversarial Robustness

Provably Robust Adversarial Examples

2020-07-23 · ICLR 2022 4 · Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr, Martin Vechev

We introduce the concept of provably robust adversarial examples for deep neural networks - connected input regions constructed from standard adversarial examples which are guaranteed to be robust to a set of real-world …

Structured Universal Adversarial Attacks on Object Detection for Video Sequences

2025-10-16 · Sven Jacob, Weijia Shao, Gjergji Kasneci arxiv

Video-based object detection plays a vital role in safety-critical applications. While deep learning-based object detectors have achieved impressive performance, they remain vulnerable to adversarial attacks, particularl…

Video Object DetectionAdversarial Attack

Provable defenses against adversarial examples via the convex outer adversarial polytope

2017-11-02 · ICML 2018 7 · Eric Wong, J. Zico Kolter

We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training data. For previously unseen examples, the approach is guaranteed to detect …

Adversarial Attack