AIAI Governance StackFree kit

TrojAI

Enterprise AI security combining automated red teaming with real-time application protection

Red-Teaming & AI Security
Visit website ↗

What TrojAI does

TrojAI is an enterprise AI security company that pairs automated red teaming with runtime protection to secure AI models and applications across their lifecycle. Founded in 2020 by James Stewart and Stephen Goddard in Saint John, New Brunswick (with a Boston office), the company built its platform around two core products: TrojAI Detect, which automatically red-teams AI models and applications during development to find and fix vulnerabilities, and TrojAI Defend, a real-time AI firewall that protects deployed applications against threats such as prompt injection, data leakage, and model poisoning. The combination lets organizations both harden AI before release and guard it in production, addressing the reality that adversarial risk spans build and run phases. TrojAI targets enterprise security, risk, and ML teams adopting generative AI and LLM applications who need protection that fits existing security operations. The company raised $5.75M in seed funding in April 2024 led by Flying Fish Partners, bringing total funding to roughly $11.4M, and was acquired by A10 Networks in 2026, positioning its technology within a broader application-security and networking portfolio. Its distinguishing strength is unified coverage across pre-deployment testing and runtime defense.

Key capabilities

  • Automated model red teaming (TrojAI Detect)
  • Real-time AI firewall (TrojAI Defend)
  • Prompt injection and data leakage protection
  • Model poisoning defense
  • Vulnerability remediation

Best for

Enterprises wanting combined pre-deployment red teaming and runtime AI application protection

Limitations

Now part of A10 Networks, so future roadmap is tied to the acquirer; standalone framework/compliance mapping is limited publicly.

Framework coverage

TrojAI does not publish explicit mappings to the major AI governance frameworks. That is common for tools in the red-teaming & ai security category, where the value is technical rather than documentary — but it means you will be responsible for evidencing how it satisfies your obligations.

Compare TrojAI

Head-to-head against the closest tools in its category.

TrojAI alternatives

Other tools solving a similar problem in Red-Teaming & AI Security.

Cranium AI

End-to-end AI security and governance platform to discover, monitor, red-team and prove enterprise AI

EU AI ActNIST AI RMFISO/IEC 42001

Mindgard

Continuous automated AI red teaming and security testing for enterprise AI systems

SOC 2

Protect AI

End-to-end security for the AI and machine-learning supply chain

NIST AI RMFSOC 2Open-source

Robust Intelligence

AI Firewall and automated model validation to secure AI from build to production

NIST AI RMF

Promptfoo

Open-source tool for evaluating and red-teaming LLM apps, agents, and RAG systems

Open-source

Adversa AI

Continuous AI red teaming for agents, LLMs, and generative AI applications

See the full TrojAI alternatives guide →

AI Governance Tool Selection Kit

A vendor-comparison worksheet plus EU AI Act, NIST AI RMF and ISO/IEC 42001 requirement checklists — so you can shortlist tools against the obligations that actually apply to you.

Free. No spam — unsubscribe anytime.