The DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.
LEMNA: Explaining Deep Learning based Security Applications
Open accessAbstract
While deep learning has shown a great potential in various domains, the lack of transparency has limited its application in security or safety-critical areas. Existing research has attempted to develop explanation techniques to provide interpretable explanations for each classification decision. Unfortunately, current methods are optimized for non-security tasks ( e.g., image analysis). Their key assumptions are often violated in security applications, leading to a poor explanation fidelity. In this paper, we propose LEMNA, a high-fidelity explanation method dedicated for security applications. Given an input data sample, LEMNA generates a small set of interpretable features to explain how the input sample is classified. The core idea is to approximate a local area of the complex deep learning decision boundary using a simple interpretable model. The local interpretable model is specially designed to (1) handle feature dependency to better work with security applications ( e.g., binary code analysis); and (2) handle nonlinear local boundaries to boost explanation fidelity. We evaluate our system using two popular deep learning applications in security (a malware classifier, and a function start detector for binary reverse-engineering). Extensive evaluations show that LEMNA's explanation has a much higher fidelity level compared to existing methods. In addition, we demonstrate practical use cases of LEMNA to help machine learning developers to validate model behavior, troubleshoot classification errors, and automatically patch the errors of the target models.
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
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
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
Jolliffe, I. T. (1986) · Springer Series in Statistics · doi:10.1007/978-1-4757-1904-8 · Cited by 8,273
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
Olshausen, B. A., & Field, D. J. (1996) · Nature · doi:10.1038/381607a0 · Cited by 5,694 · cited 1×
“As a side note, we want to clarify that machine learning explanation is completely different from feature selection methods such as Principal Component Analysis (PCA) [26], Sparse Coding [39] or Chi-square Statistics [49].”
Method
Cited by
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
Wang, B., Yao, Y., Shan, S., Li, H., Viswanath, B., Zheng, H., & Zhao, B. Y. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00031 · Cited by 1,368
Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey
Liu, H., & Lang, B. (2019) · Applied Sciences · doi:10.3390/app9204396 · Cited by 1,133
“These models report only the detection results and have no interpretable basis [93].”
BackgroundDeep Learning Based Vulnerability Detection: Are We There Yet?
Chakraborty, S., Krishna, R., Ding, Y., & Ray, B. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2021.3087402 · Cited by 790
STRIP: a defence against trojan attacks on deep neural networks
Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D. C., & Nepal, S. (2019) · Proceedings of the 35th Annual Computer Security Applications Conference · doi:10.1145/3359789.3359790 · Cited by 707
Deep Learning Based Attack Detection for Cyber-Physical System Cybersecurity: A Survey
Zhang, J., Pan, L., Han, Q.-L., Chen, C., Wen, S., & Xiang, Y. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1004261 · Cited by 432
An Explainable Machine Learning Framework for Intrusion Detection Systems
Wang, M., Zheng, K., Yang, Y., & Wang, X. (2020) · IEEE Access · doi:10.1109/access.2020.2988359 · Cited by 355
Explainable Artificial Intelligence in CyberSecurity: A Survey
Capuano, N., Fenza, G., Loia, V., & Stanzione, C. (2022) · IEEE Access · doi:10.1109/access.2022.3204171 · Cited by 330
A Survey of Android Malware Detection with Deep Neural Models
Qiu, J., Zhang, J., Luo, W., Pan, L., Nepal, S., & Xiang, Y. (2021) · ACM Computing Surveys · doi:10.1145/3417978 · Cited by 321
Analyzing Adversarial Attacks against Deep Learning for Intrusion Detection in IoT Networks
Ibitoye, O., Shafiq, O., & Matrawy, A. (2019) · 2019 IEEE Global Communications Conference (GLOBECOM) · doi:10.1109/globecom38437.2019.9014337 · Cited by 281
“However, two major challenges of deep learning in security applications are the lack of transparency of the deep learning models [3], and the vulnerability of the deep learning models to adversarial attacks [4].”
BackgroundWhen Machine Unlearning Jeopardizes Privacy
Chen, M., Zhang, Z., Wang, T., Backes, M., Humbert, M., & Zhang, Y. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484756 · Cited by 195
Explainable artificial intelligence for cybersecurity: a literature survey
Charmet, F., Tanuwidjaja, H. C., Ayoubi, S., Gimenez, P.-F., Han, Y., Jmila, H., Blanc, G., Takahashi, T., & Zhang, Z. (2022) · Annals of Telecommunications · doi:10.1007/s12243-022-00926-7 · Cited by 167
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
Salem, A., Bhattacharya, A., Backes, M., Fritz, M., & Zhang, Y. (2020) · Universität des Saarlandes · doi:10.22028/d291-47370 · Cited by 157
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
“On the other hand, the white-box condition makes sense when the one seeking interpretations is the model owner.”
InfluentialHidden Backdoors in Human-Centric Language Models
Li, S., Liu, H., Dong, T., Zhao, B. Z. H., Xue, M., Zhu, H., & Lu, J. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484576 · Cited by 119
“The adversaries’ success is exacerbated by the untrustworthy supply chain and poor interpretability of such complicated large language models, further raising security concerns [3, 6, 17, 43, 44, 68].”
BackgroundBlack Box Attacks on Explainable Artificial Intelligence(XAI) methods in Cyber Security
Kuppa, A., & Le-Khac, N.-A. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206780 · Cited by 123
Text Backdoor Detection Using an Interpretable RNN Abstract Model
Fan, M., Si, Z., Xie, X., Liu, Y., & Liu, T. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3103064 · Cited by 38
Eavesdrop the Composition Proportion of Training Labels in Federated Learning
Wang, L., Xu, S., Wang, X., & Zhu, Q. (2019) · arXiv · doi:10.48550/arxiv.1910.06044 · Cited by 34
A Model-Agnostic Approach for Explaining the Predictions on Clustered Data
Zhou, Z., Sun, M., & Chen, J. (2019) · 2019 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2019.00202 · Cited by 5
“A very recent model-agnostic approach LEMNA [5] proposes a high-fidelity explanation method dedicated for security applications.”
MethodInfluential
Metadata
- Authors
- Guo, W., Mu, D., Xu, J., Su, P., Wang, G., & Xing, X.
- Venue
- Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2018-10-15
- Pages
- 364-379
- OpenAlex
- W2890991187
- Cited by
- 287
- References
- 59
- FWCI
- 11.13
- Type
- conference paper
- Language
- en
- Open access
- bronze
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
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.