CVE-2024-45436

Ollama CVE-2024-45436 エクスプロイト Ollama ZIP トラバーサル脆弱性 CVE-2024-45436 に対するクリーンで効率的なエクスプロイト実装です。 中国語ドキュメント：READMECN.md 脆弱性の説明 CVE-2024-45436 は、Ollama バージョン 0.1.47 未満におけるパストラバーサル脆弱性（別名「Zip Slip」）です。この脆弱性により、攻撃者は ZIP ファイル展開操作時のパス検証不備を悪用して、ファイルシステム上の任意の場所にファイルを書き込むことができます。 この欠陥は、モデルファイルを展開する Ollama の...

offensive-ai-compilation

攻击性 AI 汇编 一份涵盖攻击性 AI 的有用资源精选列表。 📁 目录 📁 🚫 滥用 🚫 🧠 对抗性机器学习 🧠 ⚡ 攻击 ⚡ 🔒 提取 🔒 ⚠️ 局限性 ⚠️ 🛡️ 防御措施 🛡️ 🔗 有用链接 🔗 ⬅️ 反转（或推断）⬅️ 🛡️ 防御措施 🛡️ 🔗 有用链接 🔗 💉 投毒 💉 🔓 后门 🔓 🛡️ 防御措施 🛡️ 🔗 有用链接 🔗 🏃‍♂️ 规避 🏃‍♂️ 🛡️ 防御措施 🛡️ 🔗 有用链接 🔗 🛠️ 工具 🛠️ ART Cleverhans 🔧 使用 🔧 🕵️‍♂️ 渗透测试 🕵️‍♂️ 🦠 恶意软件 🦠 🗺️ OSINT 🗺️ 📧 钓鱼 📧 👨‍🎤 生成式 AI 👨‍🎤 🔊 音频 🔊...

ai-kill-chain

AI時代の脅威に対応する拡張サイバーキルチェーン LLMおよびエージェント型AI攻撃に対抗する防御側のための、Lockheed Martin Cyber Kill Chainのアップデート。モデルサプライチェーンの侵害に対応する攻撃前段階を追加。元の7段階それぞれにAI固有のサブテクニックを追加。Actions on Objectives段階を3つの対等なサブ段階に分割：従来型データ窃取、モデル抽出、エージェント型ピボット。 著者: Gourav Nagar バージョン: 1.0 日付: 2026年5月19日 リポジトリ:...

MEA-Bench

MEA-Bench：模型提取攻击基准 本仓库为模型提取攻击、防御、自适应攻击和评估提供了统一的基准。公共接口围绕少量可移植命令进行组织。特定方法的 Python 模块和旧版运行脚本属于实现细节，而非面向用户的入口点。 以下四个可移植入口点会验证其公共参数，然后分派到方法实现。Slurm 资源包装器被有意排除在外。方法自有的清单文件在恢复行为和产物溯源方面仍具有权威性。 论文与作者 针对 LLM 提取的防御能否跨攻击生效？黑盒模型提取的生命周期基准 Shuze Liu（佛罗里达州立大学）、Kaixiang Zhao（杨百翰大学）、 Runyang Xu（密歇根大学安娜堡分校）、Jingzh...

ai-security-battle

🤖 AIセキュリティバトルシステム レッドチーム vs ブルーチーム：敵対的ML戦闘シミュレーション レッドチームの攻撃者とブルーチームの防御者が30分間のAI/MLセキュリティ戦闘シナリオで戦う、包括的な敵対的機械学習セキュリティシミュレーションです。 🎯 プロジェクト概要 このシステムは、以下のような現実世界のAI/MLセキュリティシナリオをシミュレーションします： 🔴 レッドチーム は高度な攻撃（敵対的入力、モデル抽出、回避）を実行 🔵 ブルーチーム はMLベースの防御（異常検知、レート制限、入力検証）を展開...

Do Defenses against LLM Extraction Work across Attacks? A Lifecycle Benchmark of Black-Box Model Extraction

Large language models LLMs deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabilities. While prior work has developed diverse attacks and defenses, evaluations remain fragmented across access...

PrivacyRaven

注意：此项目已暂停。 PrivacyRaven 是一个用于深度学习系统的隐私测试库。 您可以用它来确定模型对不同隐私攻击的敏感性；评估隐私保护机器学习技术；开发新颖的隐私度量与攻击方法；以及将攻击方法重新用于数据溯源和其他用例。 PrivacyRaven 支持仅标签的黑盒模型提取、成员推断攻击，以及（即将推出的）模型反演攻击。 我们还计划加入差分隐私验证、自动化超参数优化、更多类别的攻击以及其他功能；更多信息请参阅 GitHub issues。 PrivacyRaven 曾在 OpenMined 隐私会议、Empire Hacking 和 Trail of Bits 博客 上亮相。...

AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses

Ensuring the protection of Artificial Intelligence AI models deployed in military Command and Control C2 systems and critical infrastructure is essential for maintaining information superiority. Model Extraction Attacks MEAs pose a significant threat, as they enable adversaries to replicate...

Anthropic Claims Chinese AI Firms ‘Distilled’ Claude to Train Their Models

Anthropic claims Chinese AI firms distilled Claude to train rival AI models, raising concerns about model extraction, security risks, and AI distillation abuse...

Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment

Due to hardware and software improvements, an increasing number of AI models are deployed on-device. This shift enhances privacy and reduces latency, but also introduces security risks distinct from traditional software. In this article, we examine these risks through the real-world case study of...

Measuring the Vulnerability Disclosure Policies of AI Vendors

As AI is increasingly integrated into products and critical systems, researchers are paying greater attention to identifying related vulnerabilities. Effective remediation depends on whether vendors are willing to accept and respond to AI vulnerability reports. In this paper, we examine the...

LLM4MEA: Data-Free Model Extraction Attacks on Sequential Recommenders Via Large Language Models

Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks MEAs. MEAs collect responses from recommender systems to replicate their functionality, enabling unauthorized deployments and posing critical privacy and security risks. Black-box...

Entangled Threats: a Unified Kill Chain Model for Quantum Machine Learning Security

Quantum Machine Learning QML systems inherit vulnerabilities from classical machine learning while introducing new attack surfaces rooted in the physical and algorithmic layers of quantum computing. Despite a growing body of research on individual attack vectors - ranging from adversarial poisoni...

BarkBeetle: Stealing Decision Tree Models with Fault Injection

Machine learning models, particularly decision trees DTs, are widely adopted across various domains due to their interpretability and efficiency. However, as ML models become increasingly integrated into privacy-sensitive applications, concerns about their confidentiality have grown, particularly...

CEGA: a Cost-Effective Approach for Graph-Based Model Extraction and Acquisition

Graph Neural Networks GNNs have demonstrated remarkable utility across diverse applications, and their growing complexity has made Machine Learning as a Service MLaaS a viable platform for scalable deployment. However, this accessibility also exposes GNN to serious security threats, most notably...

GradEscape: a Gradient-Based Evader against AI-Generated Text Detectors

In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text AIGT detectors. GradEscape overcomes the undifferentiable computation problem, caused by the discrete nature of text, by introducing a novel approach to construct weighted embeddings for t...

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property IP of machine-learning-as-a-service MLaaS providers. Defending against such attacks is challenging, as it must balance efficiency, robustness, and utility...

RADEP: a Resilient Adaptive Defense Framework against Model Extraction Attacks

Machine Learning as a Service MLaaS enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks, where adversaries repeatedly query the application programming...

Evaluating Query Efficiency and Accuracy of Transfer Learning-Based Model Extraction Attack in Federated Learning

Federated Learning FL is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property IP threats. Model extraction ME attacks pose a significant risk to Machine Learning as a Service MLaaS platforms, enabling attackers to replicate...

On the Interplay of Explainability, Privacy and Predictive Performance with Explanation-Assisted Model Extraction

Machine Learning as a Service MLaaS has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in specialized infrastructure or expertise. However, MLaaS...