57 matches found
Uncensored-AI
Heretic: 言語モデル向け完全自動検閲除去ツール Hereticは、高価なポストトレーニングを必要とせずに、トランスフォーマーベースの言語モデルから検閲（別名「セーフティアラインメント」）を除去するツールです。 これは、方向性アブレーション（別名「アブリタレーション」、Arditi et al. 2024、Lai 2025（1、2））の高度な実装と、Optuna を利用したTPEベースのパラメータ最適化を組み合わせています。 このアプローチにより、Hereticは完全に自動的...
heretic
Heretic: 言語モデルの検閲を完全自動で除去 Hereticは、高コストな追加学習を行うことなく、Transformerベースの言語モデルから検閲（いわゆる「安全性アラインメント」）を除去するツールです。方向性アブレーション（「アブリタレーション」とも呼ばれる、Arditi et al. 2024、Lai 2025（1、2））の高度な実装と、Optunaを活用したTPEベースのパラメータ最適化を組み合わせています。 このアプローチにより、Hereticは完全に自動で...
ablation
Ablationは、Ghidra、IDA Pro、Binary Ninjaといった業界標準ツールとまったく同じコアの逆アセンブル、逆コンパイル、バイナリ解析機能を提供するリバースエンジニアリングフレームワークです。 Claude CodeやOpenAI Codexと組み合わせることで、完全自律型のリバースエンジニアリングツールへと変貌します。 機能 BERTによるセマンティック検索:...
On the Evaluation of Spiking Neural Network Configurations for Network Intrusion Detection
Network intrusion detection is a core component of modern cybersecurity infrastructure, yet the deep learning models that dominate the field are computationally demanding, motivating interest in lightweight alternatives suited to edge and neuromorphic deployment. Spiking Neural Networks SNNs are...
Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection
Large language models LLMs can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using mechanistic interpretability; analyzing the internal computations of a neural network to understand its reasoning process.Using Circuit Tracer on...
VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection
We present VulStyle, a multi-modal software vulnerability detection model that jointly encodes function-level source code, non-terminal Abstract Syntax Tree AST structure, and code stylometry CStyle features. Prior work in code representation primarily leverages token-level models or full AST...
Towards Certified Malware Detection: Provable Guarantees against Evasion Attacks
Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address this vulnerability, we propose a certifiably robust malware detection framework based on randomized smoothing through feature ablation and targeted...
Software Vulnerability Detection Using a Lightweight Graph Neural Network
Large Language Models LLMs have emerged as a popular choice in vulnerability detection studies given their foundational capabilities, open source availability, and variety of models, but have limited scalability due to extensive compute requirements. Using the natural graph relational structure o...
Agent Privilege Separation in OpenClaw: A Structural Defense against Prompt Injection
Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark Greshake et al., 2024 against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense...
PIDSMaker: Building and Evaluating Provenance-Based Intrusion Detection Systems
Recent provenance-based intrusion detection systems PIDSs have demonstrated strong potential for detecting advanced persistent threats APTs by applying machine learning to system provenance graphs. However, evaluating and comparing PIDSs remains difficult: prior work uses inconsistent preprocessi...
EUVD-2025-180335
Malicious code in areology-darkmatter-ablation-thermochronology npm...
EUVD-2025-180525
Malicious code in ablation-scripts-pino-terraforming npm...
Malicious code in dagda-ablation-ganymede-meteor (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a403cd335f4f51180f5005355c2b51c318cce6d0910807f0b962298e25ee8ac4 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...
EUVD-2025-175578
Malicious code in websockets-winston-neptune-ablation npm...
EUVD-2025-176408
Malicious code in server-weywot-ablation-ablation npm...
EUVD-2025-179261
Malicious code in dotenv-safe-jovian-astroinformatics-ablation npm...
EUVD-2025-175438
Malicious code in yonder-mineralogy-ablation-achernar npm...
Malicious code in ablation-rigel-phoenix-despina (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 4722a4aa3a2d3eabaa640988d1bb56407667f8dce22d649488a5c01657467d86 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...