Author:
Nolte Gerrit,Schlüter Maximilian,Murtovi Alnis,Steffen Bernhard
Abstract
AbstractTADS are a novel, concise white-box representation of neural networks. In this paper, we apply TADS to the problem of neural network verification, using them to generate either proofs or concise error characterizations for desirable neural network properties. In a case study, we consider the robustness of neural networks to adversarial attacks, i.e., small changes to an input that drastically change a neural networks perception, and show that TADS can be used to provide precise diagnostics on how and where robustness errors a occur. We achieve these results by introducing Precondition Projection, a technique that yields a TADS describing network behavior precisely on a given subset of its input space, and combining it with PCA, a traditional, well-understood dimensionality reduction technique. We show that PCA is easily compatible with TADS. All analyses can be implemented in a straightforward fashion using the rich algebraic properties of TADS, demonstrating the utility of the TADS framework for neural network explainability and verification. While TADS do not yet scale as efficiently as state-of-the-art neural network verifiers, we show that, using PCA-based simplifications, they can still scale to medium-sized problems and yield concise explanations for potential errors that can be used for other purposes such as debugging a network or generating new training samples.
Funder
Technische Universität Dortmund
Publisher
Springer Science and Business Media LLC
Subject
Information Systems,Software
Reference58 articles.
1. Abdi, H., Williams, L.J.: Principal component analysis. Wiley Interdiscip. Rev.: Comput. Stat. 2(4), 433–459 (2010)
2. Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (xai). IEEE Access 6, 52138–52160 (2018)
3. Albarghouthi, A., et al.: Introduction to neural network verification. Found. Trends Program. Lang. 7(1–2), 1–157 (2021)
4. Arora, R., Basu, A., Mianjy, P., Mukherjee, A.: Understanding deep neural networks with rectified linear units. Arxiv preprint (2016). arXiv:1611.01491
5. Axler, S.: Linear Algebra Done Right. Springer, Berlin (1997)
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Explanation Paradigms Leveraging Analytic Intuition (ExPLAIn);International Journal on Software Tools for Technology Transfer;2023-06
2. Towards rigorous understanding of neural networks via semantics-preserving transformations;International Journal on Software Tools for Technology Transfer;2023-05-30
3. Forest GUMP: a tool for verification and explanation;International Journal on Software Tools for Technology Transfer;2023-05-30