Evaluating Explanation Methods for Deep Learning in Security
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by developing methods for explaining the predictions of neural networks. While several of these approaches have been successfully applied in the area of computer vision, their application in security has received little attention so far. It is an open question which explanation methods are appropriate for computer security and what requirements they need to satisfy. In this paper, we introduce criteria for comparing and evaluating explanation methods in the context of computer security. These cover general properties, such as the accuracy of explanations, as well as security-focused aspects, such as the completeness, efficiency, and robustness. Based on our criteria, we investigate six popular explanation methods and assess their utility in security systems for malware detection and vulnerability discovery. We observe significant differences between the methods and build on these to derive general recommendations for selecting and applying explanation methods in computer security.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · cited 2×
“While the importance of the individual criteria depends on the particular task, we find that the methods IG [47] and LRP [5] comply best with all criteria and resemble general-purpose techniques for security systems.”
MethodGrad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
Chattopadhay, A., Sarkar, A., Howlader, P., & Balasubramanian, V. N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00097 · Cited by 3,639
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
Cited by
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Samek, W., Montavon, G., Lapuschkin, S., Anders, C. J., & Muller, K.-R. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3060483 · Cited by 1,477
“measurement artifacts or adversarial perturbations [182]; 2) resilience to drifting data distributions [49]; 3) ability to accurately assess the confidence of its own predictions [135], [139]; 4) safety and security aspects [21], [26], [84], [193]; 5) legal requirements or adherence to social norms [54], [60]; 6) abil…”
BackgroundGenerative Adversarial Networks for face generation: A survey
Kammoun, A., Slama, R., Tabia, H., Ouni, T., & Abid, M. (2022) · ACM Computing Surveys · doi:10.1145/1122445.1122456 · Cited by 311
Impact of word embedding models on text analytics in deep learning environment: a review
Asudani, D. S., Nagwani, N. K., & Singh, P. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10419-1 · Cited by 274
DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
Han, D., Wang, Z., Chen, W., Zhong, Y., Wang, S., Zhang, H., Yang, J., Shi, X., & Yin, X. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484589 · Cited by 121
“For another, existing interpretations have shown to be vulnerable to adversarial attacks [18, 47, 60] or even random noise [14, 54].”
BackgroundResultInfluentialLin, Y.-S., Lee, W.-C., & Celik, Z. B. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467213 · Cited by 64
“As [3] stated, these metrics are often either conceptual without quantitative measures such as the metrics proposed in [40] or are domain-specific focusing on malware detection and vulnerability discovery [39].”
Background
Metadata
- Authors
- Warnecke, A., Arp, D., Wressnegger, C., & Rieck, K.
- Venue
- 2020 IEEE European Symposium on Security and Privacy (EuroS&P)
- Publisher
- IEEE
- Published
- 2020-09
- Pages
- 158-174
- OpenAlex
- W3000471247
- Cited by
- 127
- References
- 17
- FWCI
- 5.95
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Evaluating Explanation Methods for Deep Learning in Security. https://app.cochat.ai/papers/10.1109/eurosp48549.2020.00018
- The paper
- Warnecke, A., Arp, D., Wressnegger, C., & Rieck, K. (2020). Evaluating Explanation Methods for Deep Learning in Security. 2020 IEEE European Symposium on Security and Privacy (EuroS&P). https://doi.org/10.1109/eurosp48549.2020.00018
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.