TrojAI provides an AI security platform that protects artificial intelligence and machine learning applications from security threats. The company's platform includes TrojAI::DETECT, which performs penetration testing of AI models before deployment to identify risks and vulnerabilities, and TrojAI::DEFEND, which protects AI applications in real-time using a comprehensive rules engine. The platform also features an AI firewall that filters traffic to and from public AI services to block, redact and audit activity. The technology helps organizations comply with benchmarks like the OWASP AI framework and privacy regulations by detecting issues such as data poisoning, prompt injection, and other emerging threats that could compromise AI systems. It safeguards against adversarial attacks that could cause AI models to misclassify data or reveal sensitive information. CB Insights named TrojAI to its AI 100 list of most promising artificial intelligence startups in April 2024.
Key customers and partnerships
TrojAI's platform protected hundreds of AI models and safeguarded AI usage for tens of thousands of employees at a Fortune 50 financial services company. The company was also selected as one of 50 vendors for the Canadian Automotive Manufacturers Association's "Project Arrow" autonomous electric vehicle initiative in 2022, where it provided cybersecurity for the autonomous driving platform alongside companies like Magna, Michelin and Microsoft. A major US regulator engaged TrojAI for a project to assess vulnerabilities across their computer vision, natural language processing, and tabular AI models.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.