paper-with-me

홈 › Papers

Empirical Quantification of Spurious Correlations in Malware Detection

2025-06-11 · Bianca Perasso, Ludovico Lozza, Andrea Ponte, Luca Demetrio, Luca Oneto, Fabio Roli

End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain knowledge. While previous work highlighted that deep networks mainly focus on metadata, none investigated the phenomenon further, without quantifying their impact on the decision. In this work, we deepen our understanding of how spurious correlation affects deep learning for malware detection by highlighting how much models rely on empty spaces left by the compiler, which diminishes the relevance of the compiled code. Through our seminal analysis on a small-scale balanced dataset, we introduce a ranking of two end-to-end models to better understand which is more suitable to be put in production.

📄 PDF Abstract BibTeX arXiv:2506.09662

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningMalware Detection

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Improving Adversarial Robustness in Android Malware Detection by Reducing the Impact of Spurious Correlations

2024-08-27 · Hamid Bostani, Zhengyu Zhao, Veelasha Moonsamy

Machine learning (ML) has demonstrated significant advancements in Android malware detection (AMD); however, the resilience of ML against realistic evasion attacks remains a major obstacle for AMD. One of the primary fac…

Adversarial RobustnessAndroid Malware DetectionDomain AdaptationMalware Detection

How to Train your Antivirus: RL-based Hardening through the Problem-Space

2024-02-29 · Ilias Tsingenopoulos, Jacopo Cortellazzi, Branislav Bošanský, Simone Aonzo 외

ML-based malware detection on dynamic analysis reports is vulnerable to both evasion and spurious correlations. In this work, we investigate a specific ML architecture employed in the pipeline of a widely-known commercia…

Malware Detection

When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs

2025-11-10 · Shaowen Wang, Yiqi Dong, Ruinian Chang, Tansheng Zhu 외 arxiv

Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet previously underexplored class of ha…

Improving Group Robustness on Spurious Correlation via Evidential Alignment

2025-06-12 · Wenqian Ye, Guangtao Zheng, Aidong Zhang

Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets. For instance, an image classifier may identify camels based on the desert ba…

Uncertainty Quantification

Mitigating Spurious Correlations via Disagreement Probability

2024-11-04 · Hyeonggeun Han, Sehwan Kim, Hyungjun Joo, Sangwoo Hong 외

Models trained with empirical risk minimization (ERM) are prone to be biased towards spurious correlations between target labels and bias attributes, which leads to poor performance on data groups lacking spurious correl…