paper-with-me

Papers

Logit Pairing Methods Can Fool Gradient-Based Attacks

2018-10-29 · Marius Mosbach, Maksym Andriushchenko, Thomas Trost, Matthias Hein, Dietrich Klakow

Recently, Kannan et al. [2018] proposed several logit regularization methods to improve the adversarial robustness of classifiers. We show that the computationally fast methods they propose - Clean Logit Pairing (CLP) and Logit Squeezing (LSQ) - just make the gradient-based optimization problem of crafting adversarial examples harder without providing actual robustness. We find that Adversarial Logit Pairing (ALP) may indeed provide robustness against adversarial examples, especially when combined with adversarial training, and we examine it in a variety of settings. However, the increase in adversarial accuracy is much smaller than previously claimed. Finally, our results suggest that the evaluation against an iterative PGD attack relies heavily on the parameters used and may result in false conclusions regarding robustness of a model.

📄 PDF Abstract BibTeX arXiv:1810.12042

Code (1)

uds-lsv/evaluating-logit-pairing-methods 공식 구현 tf

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Adversarial Logit Pairing

2018-03-16 · NeurIPS 2018 · Harini Kannan, Alexey Kurakin, Ian Goodfellow

In this paper, we develop improved techniques for defending against adversarial examples at scale. First, we implement the state of the art version of adversarial training at unprecedented scale on ImageNet and investiga…

When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence

2023-11-23 · Benoit Coqueret, Mathieu Carbone, Olivier Sentieys, Gabriel Zaid

Artificial intelligence, and specifically deep neural networks (DNNs), has rapidly emerged in the past decade as the standard for several tasks from specific advertising to object detection. The performance offered has l…

Adversarial Attackobject-detectionObject Detection

Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks

2020-08-09 · Xiaosen Wang, Yichen Yang, Yihe Deng, Kun He

Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification.For text classification, however, existing synonym substitution based adversar…

Adversarial AttackImage Classificationtext-classificationText Classification

Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustness

2022-02-15 · Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil

In standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax function on the logits to get the probability s…

Adversarial Robustness

"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extens…

Adversarial Text