AML.T0000.001 · Pre-Print Repositories

閱讀 MITRE ATLAS 中 AML.T0000.001「Pre-Print Repositories」相關的 1 個 AI 資安案例,查看事件證據、適用範圍與 AIDEFEND 防禦分析。

風險分類說明

Pre-Print repositories, such as arXiv, contain the latest academic research papers that haven't been peer reviewed. They may contain research notes, or technical reports that aren't typically published in journals or conference proceedings. Pre-print repositories also serve as a central location to share papers that have been accepted to journals. Searching pre-print repositories provides adversaries with a relatively up-to-date view of what researchers in the victim organization are working on.

框架官方來源 ↗ · 開啟互動探索 ↗

Exercise ·

規避惡意程式 C&C 流量的深度學習偵測器

Palo Alto Networks 的 Security AI 研究團隊測試了一個用來從 HTTP 流量中偵測惡意程式命令與控制(C&C)通訊的深度學習模型。我們依據 Le 等人的公開論文(https://arxiv.org/abs/1802.03162),建立了一個模型,訓練資料與我們正式環境的模型相近,表現也相當。接著我們製作對抗樣本、向模型送出查詢,再依回應逐步調整樣本,直到成功規避該模型為止。

沿用 SecureFlow 來源步驟的 ATLAS 標註;不是 MITRE 對跨框架對應的背書。

SecureFlow · 閱讀完整案例 ↗