分析恶意软件表示在特征扰动下的稳定性，揭示压缩与生成模型的潜在安全风险。
Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations
- 设计潜空间扰动分析流程，评估多种表示在特征空间扰动下的行为变化。
- 发现压缩表示在扰动下更易偏离决策边界，而生成式模型提供额外诊断价值。
- 适合关注恶意软件检测鲁棒性与表示安全性的研究人员参考。
静态恶意软件检测器通常使用准确率、F1、ROC AUC 和 PR AUC 等干净样本指标进行评估，但这些指标难以揭示学习到的恶意软件表示在特征向量扰动下的行为、样本向不确定决策区域的移动程度，或压缩表示是否保留安全相关结构。本文提出针对 EMBER 特征空间中恶意软件扰动的潜空间稳定性分析流程，比较了完整 EMBER 特征、基于 PCA 的压缩、β/去噪变分自编码器表示、曼德尔布罗特启发的逃逸时间描述符以及一种 PINN 风格的潜流模块。定义了潜空间逃逸发散（LED）以衡量扰动下逃逸时间谱的变化，并利用 PINNFlow 推导的残差、速度、风险与梯度偏移指标刻画潜空间运动。实验基于 18 万训练样本、18 万测试样本和 24 万保留样本的 EMBER 静态 PE 特征向量展开。完整 EMBER 特征在干净分类中表现最优，ROC AUC 为 0.9962，F1 为 0.9713；而 PCA-64 是最强压缩基线，ROC AUC 为 0.9846，F1 为 0.9347。所提出的 VAE+Mandelbrot+PINNFlow 表示虽在干净分类中未超越基线，但在受控特征空间扰动探测下提供了额外诊断价值。
原文摘要 · Abstract (English)
Static malware detectors are commonly evaluated using clean-sample metrics such as accuracy, F1, ROC AUC, and PR AUC. However, these metrics provide limited insight into how learned malware representations behave when feature vectors are perturbed, how close samples move toward uncertain decision regions, or whether compressed representations preserve security-relevant structure. This paper presents a latent-stability analysis pipeline for malware perturbation assessment in EMBER feature space. The pipeline compares full EMBER features, PCA-based compression, beta/denoising variational autoencoder representations, Mandelbrot-inspired escape-time descriptors, and a PINN-style latent-flow module. We define Latent Escape Divergence (LED) to measure changes in escape-time profiles under perturbation, and use PINNFlow-derived residual, velocity, risk, and gradient-shift metrics to characterize latent movement. Experiments are conducted on EMBER static PE feature vectors using 180,000 training samples, 180,000 test samples, and 240,000 holdout samples. Full EMBER features achieve the strongest clean classification performance with ROC AUC of 0.9962 and F1 of 0.9713, while PCA-64 is the strongest compressed baseline with ROC AUC of 0.9846 and F1 of 0.9347. The proposed VAE+Mandelbrot+PINNFlow representation does not outperform these baselines for clean classification, but it provides additional diagnostic value under controlled feature-space perturbation probes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。