Certifiably robust malware detectors by design
Not on the map. Why?
Abstract (arXiv)
Malware analysis involves analyzing suspicious software to detect malicious payloads. Static malware analysis, which does not require software execution, relies increasingly on machine learning techniques to achieve scalability. Although such techniques obtain very high detection accuracy, they can be easily evaded with adversarial examples where a few modifications of the sample can dupe the detector without modifying the behavior of the software. Unlike other domains, such as computer vision, creating an adversarial example of malware without altering its functionality requires specific transformations. We propose a new model architecture for certifiably robust malware detection by design. In addition, we show that every robust detector can be decomposed into a specific structure, which can be applied to learn empirically robust malware detectors, even on fragile features. Our framework ERDALT is based on this structure. We compare and validate these approaches with machine-learning-based malware detection methods, allowing for robust detection with limited reduction of detection performance.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 10 Aug 2025.
Builds on
30 of 46 references.
References · 30
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2016Universal adversarial perturbationscited by 784
- 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
- 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 293
- 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 195
- 2018EMBER: An Open Dataset for Training Static PE Malware Machine Learning Modelscited by 165
- 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
- 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
- 2017Malware Detection by Eating a Whole EXEcited by 115
18 more
- 2020Opportunities and Challenges in Deep Learning Adversarial Robustness: A Surveycited by 72
- 2018Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executablescited by 62
- 2018Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learningcited by 61
- 2020Functionality-preserving Black-box Optimization of Adversarial Windows Malwarecited by 58
- 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 56
- 2017Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detectioncited by 52
- 2020Certified Monotonic Neural Networkscited by 51
- 2020SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detectioncited by 49
- 2018Exploring Adversarial Examples in Malware Detectioncited by 42
- 2020A Survey of Machine Learning Methods and Challenges for Windows Malware Classificationcited by 33
- 2019Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binariescited by 31
- 2021Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Artcited by 18
- 2020The Curious Case of Convex Neural Networkscited by 16
- 2021A Survey on Adversarial Attacks for Malware Analysiscited by 16
- 2023Decoding the Secrets of Machine Learning in Malware Classification: A Deep Dive into Datasets, Feature Extraction, and Model Performancecited by 13
- 2020Generating End-to-End Adversarial Examples for Malware Classifiers Using Explainabilitycited by 9
- 2020A survey on practical adversarial examples for malware classifierscited by 5
- 2021Realizable Universal Adversarial Perturbations for Malwarecited by 5
Built on by
Not cited yet.