SecML

SecML: Uma biblioteca para Aprendizado de Máquina Seguro e Explicável SecML é uma biblioteca Python de código aberto para a avaliação de segurança de algoritmos de Aprendizado de Máquina ML. Ela vem com um conjunto de recursos poderosos: Ampla gama de algoritmos de ML suportados. Todos os...

AI-Red-Teaming-Playground-Labs

AI रेड टीमिंग प्लेग्राउंड लैब्स इस रिपॉजिटरी में "AI Red Teaming in Practice" पाठ्यक्रम में उपयोग किए जाने वाले labs की चुनौतियाँ शामिल हैं। यह पाठ्यक्रम मूल रूप से Black Hat USA 2024 में Dr. Amanda Minnich और Gary Lopez द्वारा पढ़ाया गया था। Martin Pouliot ने चुनौतियों के लिए बुनियादी ढाँचे और...

ai-llm-red-team-handbook

AI / LLM Red Team फील्ड मैनुअल और सलाहकार हैंडबुक बड़े भाषा मॉडल LLM, AI एजेंट, RAG पाइपलाइन और AI-सक्षम अनुप्रयोगों पर AI/LLM रेड टीम मूल्यांकन करने के लिए एक व्यापक संचालनात्मक टूलकिट। यह रिपॉजिटरी सामरिक क्षेत्र मार्गदर्शन और रणनीतिक परामर्श ढाँचे दोनों प्रदान करती है। 📖 GitBook नेविगेशन: पूर्...

SECUREVENT: Hybrid AI/ML Security Monitoring for Distributed Event-Based Systems

Distributed event-based systems have become a common substrate for Internet-scale publish/subscribe services, IoT telemetry, cloud-native microservices, and security operations pipelines. Their loose coupling and asynchronous delivery improve scalability, but they also expand the attack surface:...

New whitepaper outlines the taxonomy of failure modes in AI agents

We are releasing a taxonomy of failure modes in AI agents to help security professionals and machine learning engineers think through how AI systems can fail and design them with safety and security in mind. The taxonomy continues Microsoft AI Red Team's work to lead the creation of systematizati...

Cyberattacks against machine learning systems are more common than you think

Machine learning ML is making incredible transformations in critical areas such as finance, healthcare, and defense, impacting nearly every aspect of our lives. Many businesses, eager to capitalize on advancements in ML, have not scrutinized the security of their ML systems. Today, along with...

Cyberattacks against machine learning systems are more common than you think

Machine learning ML is making incredible transformations in critical areas such as finance, healthcare, and defense, impacting nearly every aspect of our lives. Many businesses, eager to capitalize on advancements in ML, have not scrutinized the security of their ML systems. Today, along with...