OpenAI Blog August 22, 2019

Testing robustness against unforeseen adversaries

We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. Our method yields a new metric, UAR (Unforeseen Attack Robustness), which evaluates the robustness of a single model against an unanticipated attack, and highlights the need to measure performance across a more diverse range of unforeseen attacks.

Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.

safety

arXiv AI

Jun 2

CEAR: Certified Ensemble Adversarial Robustness in DNNs

arXiv:2606. 01437v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are highly susceptible to adversarial perturbations, leading to extensive research on robustness for safety-critical applications.

By Daniel Sadig, Mohammadreza Maleki, Hamed Karimi, Reza Samavi

benchmarks safety

arXiv Machine Learning

Jun 2

A unifying Bayesian framework for adversarial robustness

arXiv:2510. 09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge.

By Pablo G. Arce, Roi Naveiro, David R\'ios Insua

benchmarks safety

arXiv Machine Learning

Jun 26

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.

By Srishti Gupta, Zhang Chen, Luca Demetrio, Fabio Brau, Xiaoyi Feng, Zhaoqiang Xia, Antonio Emanuele Cin\`a, Maura Pintor, Luca Oneto, Ambra Demontis, Battista Biggio, Fabio Roli

safety

arXiv Machine Learning

Jun 11

Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems

arXiv:2606. 12075v1 Announce Type: cross Abstract: Network Intrusion Detection Systems (NIDS) heavily utlize Machine Learning (ML) but ML models can be manipulated via adversarial attacks.

By Mayank Raj, Nathaniel D. Bastian, Lance Fiondella, Gokhan Kul

safety

arXiv Machine Learning

Jul 7

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.

By Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt

benchmarks safety

arXiv AI

Jul 17

Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks

arXiv:2607. 14921v1 Announce Type: cross Abstract: Machine learning models are increasingly adapted in various domains.

By Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh

benchmarks safety

Related stories

CEAR: Certified Ensemble Adversarial Robustness in DNNs

A unifying Bayesian framework for adversarial robustness

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks