mlsanityData to 7 Oct 2026

Can We Rely on AI?

arXiv 2308.15092 ↗First posted 29 Aug 2023math.NA cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Over the last decade, adversarial attack algorithms have revealed instabilities in deep learning tools. These algorithms raise issues regarding safety, reliability and interpretability in artificial intelligence; especially in high risk settings. From a practical perspective, there has been a war of escalation between those developing attack and defence strategies. At a more theoretical level, researchers have also studied bigger picture questions concerning the existence and computability of attacks. Here we give a brief overview of the topic, focusing on aspects that are likely to be of interest to researchers in applied and computational mathematics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

22 of 33 references.

References · 22

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Adversarial examples in the physical worldcited by 1,762
  5. 2016Universal adversarial perturbationscited by 774
  6. 2017One pixel attack for fooling deep neural networkscited by 579
  7. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  8. 2023Are aligned neural networks adversarially aligned?cited by 305
  9. 2019Explanations can be manipulated and geometry is to blamecited by 215
  10. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  11. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 152
  12. 2018Are adversarial examples inevitable?cited by 113
10 more
  1. 2015Learning with a Strong Adversarycited by 68
  2. 2020DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flipscited by 53
  3. 2017Art of singular vectors and universal adversarial perturbationscited by 49
  4. 2021Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box settingcited by 20
  5. 2021The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networkscited by 16
  6. 2023A LLM Assisted Exploitation of AI-Guardiancited by 14
  7. 2020On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systemscited by 13
  8. 2021The Feasibility and Inevitability of Stealth Attackscited by 12
  9. 2022Gamma-convergence of a nonlocal perimeter arising in adversarial machine learningcited by 10
  10. 2023Adversarial Ink: Componentwise Backward Error Attacks on Deep Learningcited by 7

Built on by

Not cited yet.