StealthRL

StealthRL: AI 텍스트 감지기를 다중 탐지기 회피를 위한 강화학습 기반 패러프레이즈 공격 논문 arXiv 데모 모델 Hugging Face 벤치마크 데이터셋 Hugging Face 초록 AI 텍스트 감지기는 점점 더 중요한 환경에서 사용되고 있지만, 의미를 보존하는 적대적 재작성에 대한 견고성은 여전히 불확실합니다. 우리는 적응형 패러프레이즈 공격을 통해 AI 텍스트 감지기를 스트레스 테스트하는 강화학습 프레임워크인 StealthRL을 소개합니다. StealthRL은 의미적 내용을 보존하면서 감지기 앙상블에 대해...

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 &...

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...

deep-pwning

Deep-pwning은 동기화된 공격자에 대한 모델의 견고성을 평가하는 것을 목표로 기계 학습 모델을 실험하기 위한 경량 프레임워크입니다. 현재 상태의 deep-pwning은 성숙이나 완성에 절대 가깝지 않습니다. 이는 여러분이 실험하고 확장하고 발전시킬 수 있는 도구입니다. 그래야만 비로소 이 도구가 진정한 통계적 기계 학습 모델을 위한 침투 테스트 도구 모음이 될 수 있습니다. 배경 연구자들은 기계 학습 모델분류기, 군집기, 회귀기 등을 객관적으로 잘못된 결정을 내리도록 속이는 것이 놀라울 정도로 간단하다는 것을 발견했습니...

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...

QuasarNix

QuasarNix: 역공격에 강건한 Living-off-the-Land 리버스 셸 탐지 Dmitrijs Trizna · Luca Demetrio · Battista Biggio · Fabio Roli 개요 Linux living-off-the-land LOTL 리버스 셸은 합법적인 바이너리bash, python, nc, …를 악용하여 은밀한 아웃바운드 연결을 설정하므로, 시그니처 기반 탐지는 새로운 변종 및 회피 시도에 대해 신뢰할 수 없습니다. QuasarNix는 이 분야의 두 가지 공개된 격차를 해결합니다: 1. 공개된 M...

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...

stegowiper

stegoWiper: 스테고멀웨어를 무력화하는 강력하고 유연한 능동 공격 지난 10년 동안 많은 위협 그룹이 스테고멀웨어 또는 기타 스테가노그래피 기반 기술을 사용하여 전 세계 모든 분야의 조직을 공격해 왔습니다. 몇 가지 예는 다음과 같습니다: APT15/Vixen Panda, APT23/Tropic Trooper, APT29/Cozy Bear, APT32/OceanLotus, APT34/OilRig, APT37/ScarCruft, APT38/Lazarus Group, Duqu Group, Turla, Vawtrack,...

craw

CRAW: Codec Robust Audio Watermarking Source code for CRAW , a robust audio watermarking method built on STFT-magnitude-domain embedding. An encoder embeds a binary message into an audio clip's magnitude spectrogram phase is preserved from the clean signal; a decoder recovers the message under a...

APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry

Large language model LLM agents could help security operations centers SOCs investigate advanced persistent threats APTs by turning weak leads into evidence for intrusion scoping and response. Yet success under one telemetry setting does not establish robustness to changes in log collection,...

CVE-2026-80900

In the Linux kernel, the following vulnerability has been resolved: ASoC: SDCA: Make UMP message size check more robust If message offset was larger than the buffer length the size check will pass incorrectly. Refactor the check such that it is more robust to invalid sizes...

Johnny Still Receives Spam SMS: Assessing the Robustness of SMS Spam Detection

SMS spam detection systems often achieve high accuracy in controlled environments but struggle against adversarial attacks and increasingly sophisticated spam tactics in real-world deployments. In this paper, we evaluate the robustness of SMS anti-spam systems that end users actually rely on,...

Unbreakable Enterprise kernel security update

6.12.0-204.92.4.4.3 - KVM: x86: Check for invalid/obsolete root after making MMU pages available Sean Christopherson Orabug: 39832878 CVE-2026-64561 - x86/bugs: Make Safe-RET robust against interrupt injection Borislav Petkov AMD Orabug: 39832867 CVE-2026-68480 6.12.0-204.92.4.4.2 - net: tap: set...

[SECURITY] Fedora 44 Update: mir-2.26.0-2.fc44

Mir is a Wayland display server toolkit for Linux systems, with a focus on efficiency, robust operation, and a well-defined driver model...

DNG Generator for Floating-Point Edge Cases and Image Processing Robustness Testing

This C program implements an experimental TIFF/DNG file generator intended for studying how image-processing pipelines respond to unusual metadata combinations and extreme floating-point conditions...

Font Generator for Embedded Bitmap and Color Glyph Pipeline Robustness Testing

This Python program constructs a handcrafted TrueType font file that combines multiple font subsystems - including embedded bitmap tables, color glyph definitions, glyph mapping structures, and minimal layout metadata - into a single synthetic test artifact...

ACPM Transfer Validation and Stress Testing Proof of Concept

This C program is a controlled stress-testing proof of concept designed to evaluate robustness, parameter validation, and stability of the acpmdoxfer interface under repeated high-volume calls and intentionally oversized transfer descriptors...

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...