LLM Firewall & Prompt Security
Products that protect large language models (LLMs) from prompt injection, jailbreaks and data leakage, including AI red teaming.
Alice (formerly ActiveFence)
Israeli AI security company (rebranded from ActiveFence in January 2026) offering a lifecycle platform to test, guard, and…
Lakera
LLM security platform providing prompt-injection detection and real-time guardrails for generative AI applications, acquired by Check Point.
NeuralTrust
NeuralTrust is a Barcelona-based AI security startup that builds a Generative Application Firewall and agent-permissioning controls to protect…
TrojAI
AI/LLM security platform that scans models for vulnerabilities before deployment and inspects prompts and outputs at runtime to…
Haize Labs
Automated AI red-teaming company that stress-tests language models and agents for jailbreaks and failures.
Arthur AI
Arthur provides enterprise AI agent security and governance — discovering agents across an organization, tracing their reasoning and…
DeepKeep
Tel Aviv-based AI security vendor offering a model-agnostic platform that scans, red-teams, and firewalls LLM and agentic AI…
Enkrypt AI
A Yale-PhD-founded LLM security and red-teaming specialist, acquired by Anaconda in 2026.
AIM Intelligence
Seoul-based AI security platform combining automated red-teaming and real-time guardrails, used by major Korean banks and telecoms.
Confident AI
A YC-backed startup commercializing DeepEval, a widely-used open-source framework for unit-testing, red-teaming and guardrailing LLM applications.
Adversa AI
Bootstrapped AI red-teaming and adversarial-vulnerability research firm offering continuous red-teaming for agentic AI and coding-agent security.
SplxAI
A Zagreb-founded startup that automates red-teaming for AI agents, running simulated attacks to catch prompt injection before deployment.
AIShield
AIShield tests and protects machine-learning models against adversarial attacks — model theft, evasion and data poisoning — through…
Preamble
Preamble is a veteran-led AI security firm best known for discovering and responsibly disclosing the original GPT-3 prompt-injection…
Anaconda
A Python and data-science platform that acquired Enkrypt AI in August 2026 to embed AI red-teaming and guardrails.
Repello AI
AI red-teaming startup running continuous automated adversarial testing and runtime guardrails against generative AI applications.
PromptArmor
PromptArmor is a Y Combinator-backed LLM security and compliance platform focused specifically on prompt injection, the top-ranked vulnerability…
HydroX AI
San Jose, California startup building an AI trust, risk, and security management (AI TRiSM) platform for evaluating and…