Newest papers

Q-MALDetect: Quantum Image-Based Malware Detection and Adversarial Robustness Analysis

Walid El Maouaki, Mohammad Izen, Nouhaila Innan, Alberto Marchisio, Muhammad Shafique · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26240 · cited by 0 works (OpenAlex) · open-access PDF

Korean

Quantum Effective Machine-Learning (QML) 모델은 보안 애플리케이션을 위해 점점 더 많이 고려되고 있지만, 악성 코드 분석에서 그들의 대립적 인 강도는 여전히 충분히 이해되지 않습니다.이 논문은 Q-MALDetect를 소개합니다.이 모델은 실행 가능한 실행 가능한 탈출 공격의 범위에 따라 Q-MALDetect, x86-64 실행 가능한 형식 및 링크 가능한 형식 (ELF) 바이타 이미지 표현을 위한 하이브리드 탈출 및 변형적인 양자 탐지기입니다.이 모델은 97.2%의 훈련 정밀도를 달성하지만, 공격 강도가 증가함에 따라 그 강력함은 악성 코드 공격이 78.7%의 공격 성공률 (RAS)에 도달하지 않고 악성 코드

Machine translation (Meta M2M100); the English original follows.

Abstract

Quantum machine-learning (QML) models are increasingly considered for security applications, yet their adversarial robustness in malware analysis remains insufficiently understood. This paper presents Q-MALDetect, a hybrid convolutional and variational-quantum detector for byte-image representations of x86-64 Executable and Linkable Format (ELF) binaries, and evaluates it under feature-space and a range of Grad-CAM-guided, executable-aware evasion attacks. The model achieves 97.2% training accuracy, but its robustness deteriorates as attack strength increases, with the strongest evaluated feature-space attack reaching a 78.7% attack success rate (ASR). Among executable-aware attacks, Grad-CAM-guided no-operation (NOP) insertion produces the highest conditional ASR of 32.9%. Dynamic adversarial training is the most effective evaluated defense, reducing feature-space ASR to as low as 5.0%, executable-aware ASR to 7.7%, and the sequential-attack ASR to 34.0%. In contrast, convolutional-autoencoder preprocessing increases executable-aware ASR to 39.7%, coinciding with a rise in Grad-CAM attribution mass within the mutable .text region from 35.2% to 45.7%. Ablation results reveal no monotonic relationship between qubit count and robustness, while the encoding interface modifies the learned attack surface without neutralizing the strongest attack. These findings demonstrate that the effectiveness of attacks and defenses depends strongly on the perturbation constraints and evaluation conditions. Reliable deployment of QML malware detectors therefore requires assessment against both feature-space and executable-aware attacks rather than reliance on clean accuracy or generic denoising alone.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Robustness (evolution), Malware, Adversary, Computer security, Preprocessor

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange