adversarial-robustness-toolbox

Adversarial Robustness Toolbox ART v1.20 中国語READMEはこちら フォールバック画像の説明 Adversarial Robustness Toolbox（ART）は、機械学習セキュリティのためのPythonライブラリです。ARTは、Linux Foundation AI & Data Foundation（LF AI &...

robustness

robustness パッケージ pip によるインストール: pip install robustness ドキュメントを読む: https://robustness.readthedocs.io/en/latest/index.html robustness は、ニューラルネットワークのトレーニング、評価、探索を柔軟かつ簡単に行えるようにするために、私たち（MadryLab...

robustbench

RobustBench: 標準化された敵対的ロバストネスベンチマーク Francesco Croce University of Tübingen, Maksym Andriushchenko EPFL, Vikash Sehwag Princeton University, Edoardo Debenedetti EPFL, Nicolas Flammarion EPFL, Mung Chiang Purdue University, Prateek Mittal Princeton University, Matthias Hein University of Tübingen...

Sec5GLoc

Sec5GLoc: 敵対的耐性を備えた深層学習アーキテクチャによる5G屋内測位の保護 本研究は、敵対的耐性を持つ深層学習アーキテクチャを提案することで、5G屋内測位におけるセキュリティとプライバシーの課題に取り組みます。Sec5GLocは、チャネルインパルス応答（CIR）フィンガープリンティングと到着時間差（TDoA）特徴、および既知のアンカー位置を組み合わせ、ハイブリッドCNNとマルチヘッドアテンションネットワークで処理します。この設計により、位置スプーフィングや敵対的信号改ざんなどの脅威に対する堅牢性が向上します。 図1...

QuasarNix

QuasarNix: 逆襲耐性を持つLiving-off-the-Landリバースシェル検出 Dmitrijs Trizna · Luca Demetrio · Battista Biggio · Fabio Roli 概要 Linuxの 既存ツール悪用（Living-off-the-Land, LOTL） リバースシェルは、正規のバイナリ（bash、python、ncなど）を悪用して隠密な送信接続を確立するため、シグネチャベースの検出は新たな亜種や回避試行に対して信頼性が低くなります。QuasarNixは、この分野における2つの未解決のギャップに対処します。 1...

StealthRL

StealthRL: 複数のAIテキスト検出器を回避する強化学習パラフレーズ攻撃 論文（arXiv） デモ モデル（Hugging Face） ベンチマークデータセット（Hugging Face 要約...

The Chronicles of Radio Frequency Fingerprinting

Radio Frequency Fingerprinting RFF has evolved from an early idea for radar emitter identification into a broad research field for wireless device identification and spectrum monitoring for security. Rather than presenting a conventional literature survey, this work provides a critical historical...

CVE-2026-31229

A flaw was found in the Adversarial Robustness Toolbox ART, specifically within its Kubeflow component. This vulnerability, categorized as insecure deserialization CWE-502, occurs when loading model weights without proper security restrictions. A remote attacker can exploit this by uploading a...

CVE-2026-31230

A flaw was found in Adversarial Robustness Toolbox ART. This command-line argument injection vulnerability exists in its Kubeflow component due to the unsafe use of the eval function, which parses string values from --clipvalues and --inputshape arguments. A remote attacker can exploit this by...

CVE-2026-31228

A flaw was found in the Adversarial Robustness Toolbox ART, specifically within its Kubeflow component. The robustness evaluation function for PyTorch models uses the eval function to dynamically evaluate user-supplied strings for the LossFn and Optimizer parameters without proper sanitization. A...

Operationalizing Cyber Attack Prediction: A Gap-Prioritized Framework with Dataset and Model Selection Guidelines

While AI and machine learning for cyber attack prediction have advanced, a critical gap persists between theoretical research and practical operational deployment. Building on Ankalaki et al. 2025, this paper provides a comprehensive analysis of 150+ benchmark datasets and 200+ studies to identif...

Adversarial Vulnerability under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection

We present a longitudinal, drift-aware evaluation of adversarial robustness across more than a decade of Android applications using static and dynamic feature representations extracted from emulator and real-device executions. The dataset is organized into yearly slices and evaluated under three...

Deserialization of Untrusted Data

Overview adversarial-robustness-toolbox is a Toolbox for adversarial machine learning. Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the model loading process. An attacker can execute arbitrary code by uploading a maliciously crafted model file to an...

adaro-rl (0.3.0), advermorel (>=0.1.1, <=0.1.6) +16 more potentially affected by CVE-2026-31229 via adversarial-robustness-toolbox (>=0.5.0, <=1.20.1)

adversarial-robustness-toolbox PYPI version =0.5.0, =0.1.1, =0.1.0, =0.0.5, =24.6.0, =23.10.1, =1.0.1, =23.7.1, =0.2.1, =1.0.0, =0.2.0, =0.3.0, =0.4.0, =0.1.0b3, =0.1.0b6 and more Source cves: CVE-2026-31229 Source advisory: SNYK:PYTHON-ADVERSARIALROBUSTNESSTOOLBOX-17675445...

EUVD-2026-29552

The Adversarial Robustness Toolbox ART thru 1.20.1 contains an insecure deserialization vulnerability CWE-502 in its Kubeflow component's model loading functionality. When loading model weights from a file e.g., model.pt during robustness evaluation, the code uses torch.load without the...

EUVD-2026-29553

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...

CVE-2026-31230

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...

CVE-2026-31228

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a remote code execution vulnerability in its Kubeflow component. The robustness evaluation function for PyTorch models uses the unsafe eval function to dynamically evaluate user-supplied strings for the LossFn and Optimizer parameters...

CVE-2026-31230

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...

CVE-2026-31230

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...