# Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs

arXiv: https://arxiv.org/abs/2604.03843 · HTML: https://mlsanity.com/paper/2604.03843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Malware Detection by Eating a Whole EXE](https://mlsanity.com/paper/1710.09435/) (2017)
- [Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN](https://mlsanity.com/paper/1702.05983/) (2017)
- [Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables](https://mlsanity.com/paper/1803.04173/) (2018)
- [A Survey on Adversarial Attacks for Malware Analysis](https://mlsanity.com/paper/2111.08223/) (2021)
- [On the Consistency of GNN Explanations for Malware Detection](https://mlsanity.com/paper/2504.16316/) (2025)
- [SoK: Leveraging Transformers for Malware Analysis](https://mlsanity.com/paper/2405.17190/) (2024)
- [Explainability Guided Adversarial Evasion Attacks on Malware Detectors](https://mlsanity.com/paper/2405.01728/) (2024)
- [Intra-Section Code Cave Injection for Adversarial Evasion Attacks on Windows PE Malware File](https://mlsanity.com/paper/2403.06428/) (2024)
- [Explainability-Informed Targeted Malware Misclassification](https://mlsanity.com/paper/2405.04010/) (2024)

## Abstract (arXiv)

Transformer-based malware detection systems operating on graph modalities such as control flow graphs (CFGs) achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial evasion attacks remains underexplored. This paper examines the vulnerability of a RoBERTa-based malware detector that linearizes CFGs into sequences of function calls, a design choice that enables transformer modeling but may introduce token-level sensitivities and ordering artifacts exploitable by adversaries. By evaluating evasion strategies within this graph-to-sequence framework, we provide insight into the practical robustness of transformer-based malware detectors beyond aggregate detection accuracy. This paper proposes a white-box adversarial evasion attack that leverages explainability mechanisms to identify and perturb most influential graph components. Using token- and word-level attributions derived from integrated gradients, the attack iteratively replaces positively attributed function calls with synthetic external imports, producing adversarial CFG representations without altering overall program structure. Experimental evaluation on small- and large-scale Windows Portable Executable (PE) datasets demonstrates that the proposed method can reliably induce misclassification, even against models trained to high accuracy. Our results highlight that explainability tools, while valuable for interpretability, can also expose critical attack surfaces in transformer-based malware detectors.