# Beyond the Wrapper: Identifying Artifact Reliance in Static Malware Classifiers using TRUSTEE

arXiv: https://arxiv.org/abs/2605.07034 · HTML: https://mlsanity.com/paper/2605.07034/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 13 of 13)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models](https://mlsanity.com/paper/1804.04637/) (2018)
- [TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time](https://mlsanity.com/paper/1807.07838/) (2018)
- [Deep Neural Network Based Malware Detection Using Two Dimensional Binary Program Features](https://mlsanity.com/paper/1508.03096/) (2015)
- [Malware Detection using Machine Learning and Deep Learning](https://mlsanity.com/paper/1904.02441/) (2019)
- [Detection of Advanced Malware by Machine Learning Techniques](https://mlsanity.com/paper/1903.02966/) (2019)
- [Assessing the Impact of Packing on Machine Learning-Based Malware Detection and Classification Systems](https://mlsanity.com/paper/2410.24017/) (2024)
- [Empirical Quantification of Spurious Correlations in Malware Detection](https://mlsanity.com/paper/2506.09662/) (2025)

## Abstract (arXiv)

Modern cybersecurity relies heavily on static machine-learning-based malware classifiers. However, transformations such as packing and other non-semantic modifications applied to executable files limit their reliability. Malware classifiers often learn these unnecessary artifacts rather than the true binary behavior because of the high association between maliciousness and packing. Moreover, these malware classifiers are black boxes, making it difficult to understand what they learn. To address this issue, we proposed a two-part framework using the post-hoc interpretability XAI tool TRUSTEE, followed by a manual analysis of the top features. We conducted several controlled experiments by varying the dataset composition ratios to understand their impact on the results. The top-ranked features across all experiments, identified by TRUSTEE, were predominantly packing artifacts, portable executable(PE) metadata, and n-grams at the string level, rather than malicious semantics. These results suggest that these malware classifiers are highly sensitive to dataset composition and can misinterpret packing as malicious behavior. Our proposed framework allows for the reproducible diagnosis of such biases and forms a guideline for building more robust and semantically meaningful malware detection models