Newest papers

Mal-AAEGAN: Adversarial Autoencoder with Double-Critic WGAN-GP for Malware Generation

Nam Hoang Thanh, Trung Pham Duy, Lam Bui Thu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26488 · cited by 0 works (OpenAlex) · open-access PDF

Korean

기계적으로 고정된 속도(ML) 바이너리 디테이너는 상대방 샘플에 취약한 것으로 알려져 있습니다. MalGAN, Mal-LSGAN, 그리고 이전의 Mal-D2GAN과 같은 상대방 샘플 (GAN)은 상대방 샘플을 조작하여 이러한 탐지기를 탐지하고 단단하게 만들 수 있지만, 그들은 $M$ 차원 바이너리 샘플 공간에 직접적으로 작동하여 불안정한 훈련, 사라지는 gradients, 그리고 제한된 다양성의 상대방 샘플을 유발합니다. 이러한 문제를 해결하기 위해 우리는 Mal-AAEGAN을 제안합니다. 첫째, 상대방 샘플 (AAE)는 $M$ 차원 바이너리 API 기능 벡터의 낮은 차원, 정규화 및

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

Abstract

Machine-learning (ML) malware detectors are known to be vulnerable to adversarial samples. Generative adversarial networks (GANs) such as MalGAN, Mal-LSGAN, and our previous Mal-D2GAN can craft adversarial malware to probe and harden these detectors, yet they operate directly on a high-dimensional, discrete binary feature space, which leads to unstable training, vanishing gradients, and adversarial samples of limited diversity. To address these problems we propose Mal-AAEGAN. First, an adversarial autoencoder (AAE) learns a low-dimensional, regularized and continuous latent representation of the $M$-dimensional binary API feature vector, and the generator performs an additive perturbation in this latent space rather than in the raw binary space. Second, training follows the Wasserstein GAN with gradient penalty (WGAN-GP) scheme using two critics: a mimic-black-box critic that inherits the role of the substitute detector and a naive critic that inherits the role of the additional detector. A decode-binarize-OR pipeline guarantees that the original API calls of the malware are preserved. The model is evaluated on two malware datasets of different input dimensionality ($M\in\{139,215\}$) against eight common ML detectors and compared, under an identical protocol, with MalGAN, Mal-LSGAN and Mal-D2GAN. Mal-AAEGAN trains stably in the continuous latent space and attains an evasion rate on par with or higher than these binary-space baselines across both datasets, while its generator stays responsive to the noise input rather than reducing to a single fixed perturbation per malware.

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

Topics: Computer science, Malware, Adversarial system, Autoencoder, Artificial intelligence, Discriminator

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