TrojAI is an AI security platform that offers two main components: TROJAI::DETECT: This tool integrates with AI and MLOps workflows to automatically penetration test AI models before production deployment. It helps identify potential risks and vulnerabilities in AI models. TROJAI::DEFEND: This component acts as an AI firewall, protecting AI applications in real-time against various threats such as data poisoning and prompt injection. It uses a rules engine backed by data science to secure AI applications and enable safe use of public AI services. The platform aims to help organizations comply with AI security frameworks and privacy regulations by testing models pre-deployment and protecting applications from sensitive data loss post-deployment.
FEATURES
EXPLORE BY TAGS
SIMILAR TOOLS
Zania is an AI-driven platform that automates security and compliance tasks using autonomous agents for security inquiries, compliance assessments, and privacy regulation adherence.
Mindgard is a continuous automated red teaming platform that enables security teams to identify and remediate vulnerabilities in AI systems, including generative AI and large language models.
Lakera is an automated safety and security assessment tool for GenAI applications
Adversa AI is a cybersecurity company that provides solutions for securing and hardening machine learning, artificial intelligence, and large language models against adversarial attacks, privacy issues, and safety incidents across various industries.
Infinity Platform / Infinity AI is an AI-powered threat intelligence and generative AI service that combines AI-powered threat intelligence with generative AI capabilities for comprehensive threat prevention, automated threat response, and efficient security administration.
LLM Guard is a security toolkit that enhances the safety and security of interactions with Large Language Models (LLMs) by providing features like sanitization, harmful language detection, data leakage prevention, and resistance against prompt injection attacks.
WhyLabs is a platform that provides security, monitoring, and observability capabilities for Large Language Models (LLMs) and AI applications, enabling teams to protect against malicious prompts, data leaks, misinformation, and other vulnerabilities.
AI Access Security is a tool for managing and securing generative AI application usage in organizations, offering visibility, control, and protection features.
Unbound is a security platform that enables enterprises to control and protect the use of generative AI applications by employees while safeguarding sensitive information.
PINNED

Checkmarx SCA
A software composition analysis tool that identifies vulnerabilities, malicious code, and license risks in open source dependencies throughout the software development lifecycle.

Orca Security
A cloud-native application protection platform that provides agentless security monitoring, vulnerability management, and compliance capabilities across multi-cloud environments.

DryRun
A GitHub application that performs automated security code reviews by analyzing contextual security aspects of code changes during pull requests.