The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks

13 September 2021

Papers citing "The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks"

20 / 20 papers shown

Title
Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability Lijia Yu Yibo Miao Yifan Zhu Xiao-Shan Gao Lijun Zhang 48 0 0 06 Mar 2025
Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization Holger Boche Vít Fojtík Adalbert Fono Gitta Kutyniok 24 0 0 12 Aug 2024
Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees I. Tyukin T. Tyukina Daniel van Helden Zedong Zheng Evgeny M. Mirkes Oliver J. Sutton Qinghua Zhou Alexander N. Gorban Penelope Allison 16 1 0 31 Jan 2024
Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement Holger Boche Adalbert Fono Gitta Kutyniok FaML 23 4 0 18 Jan 2024
Do stable neural networks exist for classification problems? -- A new view on stability in AI Z. N. D. Liu A. C. Hansen 15 0 0 15 Jan 2024
The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning Alexander Bastounis Alexander N. Gorban Anders C. Hansen D. Higham Danil Prokhorov Oliver J. Sutton I. Tyukin Qinghua Zhou OOD 6 4 0 13 Sep 2023
How adversarial attacks can disrupt seemingly stable accurate classifiers Oliver J. Sutton Qinghua Zhou I. Tyukin Alexander N. Gorban Alexander Bastounis D. Higham AAML 14 1 0 07 Sep 2023
Can We Rely on AI? D. Higham AAML 20 0 0 29 Aug 2023
Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning Lucas Beerens D. Higham AAML 7 8 0 05 Jun 2023
Ambiguity in solving imaging inverse problems with deep learning based operators David Evangelista E. Morotti E. L. Piccolomini J. Nagy 14 8 0 31 May 2023
To be or not to be stable, that is the question: understanding neural networks for inverse problems David Evangelista J. Nagy E. Morotti E. L. Piccolomini 10 3 0 24 Nov 2022
Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game Xiao-Shan Gao Shuang Liu Lijia Yu AAML 6 0 0 17 Jul 2022
Adversarial Parameter Attack on Deep Neural Networks Lijia Yu Yihan Wang Xiao-Shan Gao AAML 14 8 0 20 Mar 2022
Limitations of Deep Learning for Inverse Problems on Digital Hardware Holger Boche Adalbert Fono Gitta Kutyniok 16 25 0 28 Feb 2022
A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks Xiaoyu Ma S. Sardy N. Hengartner Nikolai Bobenko Yen Ting Lin 9 2 0 21 Jan 2022
Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks Lijia Yu Xiao-Shan Gao AAML 11 5 0 08 Nov 2021
A Robust Classification-autoencoder to Defend Outliers and Adversaries Lijia Yu Xiao-Shan Gao AAML 14 2 0 30 Jun 2021
The Feasibility and Inevitability of Stealth Attacks I. Tyukin D. Higham Alexander Bastounis Eliyas Woldegeorgis Alexander N. Gorban AAML 4 19 0 26 Jun 2021
Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem Matthew J. Colbrook Vegard Antun A. Hansen 60 129 0 20 Jan 2021
The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems N. Gottschling Vegard Antun A. Hansen Ben Adcock 8 30 0 05 Jan 2020