Algebraic Adversarial Attacks on Explainability Models
Not on the map. Why?
Abstract (arXiv)
Classical adversarial attacks are phrased as a constrained optimisation problem. Despite the efficacy of a constrained optimisation approach to adversarial attacks, one cannot trace how an adversarial point was generated. In this work, we propose an algebraic approach to adversarial attacks and study the conditions under which one can generate adversarial examples for post-hoc explainability models. Phrasing neural networks in the framework of geometric deep learning, algebraic adversarial attacks are constructed through analysis of the symmetry groups of neural networks. Algebraic adversarial examples provide a mathematically tractable approach to adversarial examples. We validate our approach of algebraic adversarial examples on two well-known and one real-world dataset.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 16 Mar 2025.
Builds on
34 of 47 references.
References · 34
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2016Adversarial examples in the physical worldcited by 1,769
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
- 2017Adversarial Patchcited by 517
- 2017Interpretation of Neural Networks is Fragilecited by 444
- 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
- 2019Explanations can be manipulated and geometry is to blamecited by 216
- 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 175
22 more
- 2023Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Modelscited by 154
- 2021Feature Importance-aware Transferable Adversarial Attackscited by 127
- 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
- 2021Counterfactual Explanations Can Be Manipulatedcited by 113
- 2021Geometric Deep Learning on Molecular Representationscited by 113
- 2019"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanationscited by 111
- 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
- 2018How Important Is a Neuron?cited by 73
- 2022A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributionscited by 64
- 2020The Unreasonable Effectiveness of Deep Learning in Artificial Intelligencecited by 57
- 2021Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networkscited by 48
- 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
- 2021Towards the Unification and Robustness of Perturbation and Gradient Based Explanationscited by 47
- 2022Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Researchcited by 25
- 2019Bridging Adversarial Robustness and Gradient Interpretabilitycited by 22
- 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 16
- 2020Approximate Manifold Defense Against Multiple Adversarial Perturbationscited by 7
- 2024Algebraic Adversarial Attacks on Integrated Gradientscited by 4
- 2022Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insightscited by 3
- 2023Deep Learning and Geometric Deep Learning: an introduction for mathematicians and physicistscited by 3
- 2023A Testbed for Automating and Analysing Mobile Devices and their Applicationscited by 1
- 2023Defense Against Adversarial Attacks using Convolutional Auto-Encoderscited by 1
Built on by
Not cited yet.