# Realizable Universal Adversarial Perturbations for Malware

arXiv: https://arxiv.org/abs/2102.06747 · HTML: https://mlsanity.com/paper/2102.06747/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 83 references that are in the map.
- First posted on arXiv 12 Feb 2021.

## Builds on (most cited first, 30 of 40)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Adversarial Training and Robustness for Multiple Perturbations](https://mlsanity.com/paper/1904.13000/) (2019)
- [EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models](https://mlsanity.com/paper/1804.04637/) (2018)
- [Physical Adversarial Examples for Object Detectors](https://mlsanity.com/paper/1807.07769/) (2018)
- [SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems](https://mlsanity.com/paper/1812.00292/) (2018)
- [DPatch: An Adversarial Patch Attack on Object Detectors](https://mlsanity.com/paper/1806.02299/) (2018)
- [Physically Realizable Adversarial Examples for LiDAR Object Detection](https://mlsanity.com/paper/2004.00543/) (2020)
- [TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time](https://mlsanity.com/paper/1807.07838/) (2018)
- [Universal Adversarial Training](https://mlsanity.com/paper/1811.11304/) (2018)
- [Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN](https://mlsanity.com/paper/1702.05983/) (2017)
- [Adversarial Objects Against LiDAR-Based Autonomous Driving Systems](https://mlsanity.com/paper/1907.05418/) (2019)
- [Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables](https://mlsanity.com/paper/1803.04173/) (2018)
- [Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning](https://mlsanity.com/paper/1801.08917/) (2018)
- [Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection](https://mlsanity.com/paper/1704.08996/) (2017)
- [NAG: Network for Adversary Generation](https://mlsanity.com/paper/1712.03390/) (2017)

## Built on by (most cited first, 5 of 5)

- [How to Train your Antivirus: RL-based Hardening through the Problem-Space](https://mlsanity.com/paper/2402.19027/) (2024)
- [Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detection](https://mlsanity.com/paper/2205.15128/) (2022)
- [On the Effectiveness of Adversarial Training on Malware Classifiers](https://mlsanity.com/paper/2412.18218/) (2024)
- [Adversarial Patterns: Building Robust Android Malware Classifiers](https://mlsanity.com/paper/2203.02121/) (2022)
- [Certifiably robust malware detectors by design](https://mlsanity.com/paper/2508.10038/) (2025)

## Abstract (arXiv)

Machine learning classifiers are vulnerable to adversarial examples -- input-specific perturbations that manipulate models' output. Universal Adversarial Perturbations (UAPs), which identify noisy patterns that generalize across the input space, allow the attacker to greatly scale up the generation of such examples. Although UAPs have been explored in application domains beyond computer vision, little is known about their properties and implications in the specific context of realizable attacks, such as malware, where attackers must satisfy challenging problem-space constraints. In this paper we explore the challenges and strengths of UAPs in the context of malware classification. We generate sequences of problem-space transformations that induce UAPs in the corresponding feature-space embedding and evaluate their effectiveness across different malware domains. Additionally, we propose adversarial training-based mitigations using knowledge derived from the problem-space transformations, and compare against alternative feature-space defenses. Our experiments limit the effectiveness of a white box Android evasion attack to ~20% at the cost of ~3% TPR at 1% FPR. We additionally show how our method can be adapted to more restrictive domains such as Windows malware. We observe that while adversarial training in the feature space must deal with large and often unconstrained regions, UAPs in the problem space identify specific vulnerabilities that allow us to harden a classifier more effectively, shifting the challenges and associated cost of identifying new universal adversarial transformations back to the attacker.