TrojAI
TrojAI helps secure AI models, applications, and agents across both AI build time and AI runtime
Develop & Experiment
AIandMe
AIandMe provides an end-to-end platform for testing, securing, and monitoring LLM-based AI systems—combining automated adversarial testing, real-time protection, and human-in-the-loop audits to ensure reliable, compliant, and safe AI deployments.
Noma Security
“Noma Security is a comprehensive application security solution for the Data and AI lifecycle. It offers , End-to-End Visibility: Scanning notebooks, source code, and other assets to inventory AI/ML resources., AI Security Posture Management: Identifying and prioritizing AI/ML risks, including misconfigurations and vulnerable models, Runtime Protection: Safeguarding AI systems with an AI Firewall against adversarial prompts, Pre-Runtime Protection: Enhancing security through dynamic red-teaming and static analysis of models and code, Governance and Compliance: Ensuring adherence to regulatory and security standards.”
SpiceDB
Open source, Google Zanzibar-inspired permissions database for scalably storing and querying fine-grained authorization data.
Infosys Responsible AI Toolkit
The Infosys Responsible AI Toolkit (Technical Guardrail) is API Based solution designed to
ensure the ethical and responsible development of AI applications. By integrating safety, security, explainability, fairness, bias and hallucination detection into AI workflows, it empowers us to build trustworthy and accountable AI systems.
Infosys Responsible AI Toolkit Read Post »
Prisma Cloud AI-SPM
Prisma Cloud AI-SPM helps organizations discover, classify, protect and govern AI-powered applications. It provides visibility into the entire AI ecosystem including model, applications and resources, to reduce the risk of data exposure and compliance breaches. By identifying model vulnerabilities and prioritizing misconfigurations, it improves the integrity of the AI security framework.
Prisma Cloud AI-SPM Read Post »
TrojAI Detect
TrojAI Detect secures AI behavior at build time. The AI security platform continuously red teams AI models to find security weaknesses in AI, ML, and GenAI models during model development before they can be exploited.
Operant 3D Runtime Defense
Operant provides runtime application defense with threat detection and remediation, automated policy enforcement, and in-line PII redaction. It secures cloud-native environments, protecting APIs, data flows, and AI workloads against emerging threats without requiring instrumentation or integrations.
Operant 3D Runtime Defense Read Post »
Pangea Sanitize
Utilize Pangea’s Sanitize service to ensure that malicious scripts, malicious links, profanity, and regulated PII are not submitted in prompt inputs, prompt responses, or in data fetched through a RAG pipeline or agentic framework.
Pangea Authorization
Pangea’s Authorization service is an access control engine that integrates with any AI application through easy-to-use APIs and SDKs. It is used to enforce access controls to LLMs, contextual data in RAG pipelines, and agent-based operations.
Pangea Authorization Read Post »
