Can we Defend Against the Unknown? An Empirical Study About Threshold
Selection for Neural Network Monitoring

v1v2 (latest)

Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoring

14 May 2024

Jérémie Guiochet

ArXiv (abs)PDF HTML

Papers citing "Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoring"

12 / 12 papers shown

Title
Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors Shuangpeng Han Mengmi Zhang 388 0 0 03 Oct 2024
Unifying Evaluation of Machine Learning Safety Monitors Joris Guérin Raul Sena Ferreira Kevin Delmas Jérémie Guiochet 70 13 0 31 Aug 2022
Evaluation of Runtime Monitoring for UAV Emergency Landing Joris Guérin Kevin Delmas Jérémie Guiochet 63 13 0 07 Feb 2022
AugLy: Data Augmentations for Robustness Zoe Papakipos Joanna Bitton AAML 75 53 0 17 Jan 2022
ReAct: Out-of-distribution Detection With Rectified Activations Yiyou Sun Chuan Guo Yixuan Li OODD 115 485 0 24 Nov 2021
Energy-based Out-of-distribution Detection Weitang Liu Xiaoyun Wang John Douglas Owens Yixuan Li OODD 273 1,375 0 08 Oct 2020
Torchattacks: A PyTorch Repository for Adversarial Attacks Hoki Kim 77 207 0 24 Sep 2020
Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data Yen-Chang Hsu Yilin Shen Hongxia Jin Z. Kira OODD 119 577 0 26 Feb 2020
Outside the Box: Abstraction-Based Monitoring of Neural Networks T. Henzinger Anna Lukina Christian Schilling AAML 93 59 0 20 Nov 2019
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks Kimin Lee Kibok Lee Honglak Lee Jinwoo Shin OODD 199 2,064 0 10 Jul 2018
Selective Classification for Deep Neural Networks Yonatan Geifman Ran El-Yaniv CVBM 106 530 0 23 May 2017
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks Dan Hendrycks Kevin Gimpel UQCV 181 3,482 0 07 Oct 2016

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.