Exposing Previously Undetectable Faults in Deep Neural Networks

1 June 2021

Papers citing "Exposing Previously Undetectable Faults in Deep Neural Networks"

7 / 7 papers shown

Title
A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Models Zhengyuan Wei Haipeng Wang Qili Zhou William Chan 34 0 0 19 Jul 2024
When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study Vincenzo Riccio Paolo Tonella AAML 16 29 0 21 Dec 2022
Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks Zhaodi Zhang Yiting Wu Siwen Liu Jing Liu Min Zhang AAML 21 11 0 21 Aug 2022
Generating and Detecting True Ambiguity: A Forgotten Danger in DNN Supervision Testing Michael Weiss A. Gómez Paolo Tonella AAML 11 6 0 21 Jul 2022
Hierarchical Distribution-Aware Testing of Deep Learning Wei Huang Xingyu Zhao Alec Banks V. Cox Xiaowei Huang OOD AAML 28 10 0 17 May 2022
Partial success in closing the gap between human and machine vision Robert Geirhos Kantharaju Narayanappa Benjamin Mitzkus Tizian Thieringer Matthias Bethge Felix Wichmann Wieland Brendel VLM AAML 40 221 0 14 Jun 2021
Constructing Unrestricted Adversarial Examples with Generative Models Yang Song Rui Shu Nate Kushman Stefano Ermon GAN AAML 176 302 0 21 May 2018