
Mindgard
Mindgard is an offensive AI security platform that security teams use to examine AI from an attacker's perspective.

Mindgard is an offensive AI security platform that security teams use to examine AI from an attacker's perspective.
Mindgard is an offensive AI security platform and a spin-out from AI security research at Lancaster University. It operates as an autonomous red teamer, examining systems from an attacker's perspective while running continuous agentic attack workflows that map, plan, and execute complex attacks.
Mindgard complements existing AppSec tools with attacker-led reconnaissance and adaptive attacks, targeting AI vulnerabilities that conventional security testing may not find. Security teams use Mindgard.


Platform securing machine learning models and AI systems against attacks.


EvoFlint provides automated red-teaming and safety evaluation for enterprise AI systems, grading each turn against policy.


Lakera AI Security Platform is an AI-native security service for protecting generative AI applications.

Platform securing machine learning models and AI systems against attacks.

EvoFlint provides automated red-teaming and safety evaluation for enterprise AI systems, grading each turn against policy.

Lakera AI Security Platform is an AI-native security service for protecting generative AI applications.

Lakera Guard is a runtime security product for large language model applications.



Armadin's platform uses autonomous AI agents to validate exploitable enterprise attack paths.



Cisco AI Defense secures enterprise AI with asset discovery, model vulnerability evaluation, and runtime guardrails.


Autonomous AI penetration testing platform that continuously finds and validates exploitable vulnerabilities.


AI Red Teaming probes AI applications and agents for security and privacy risks via multi-turn attack simulation in CI/CD pipeline.


Pentera Platform is an automated security validation platform that emulates real attacker behavior across internal, cloud, and external environments.


AQtive Guard is an AI-powered platform that detects and remediates cryptographic and non-human identity vulnerabilities across enterprise IT.


Continuous behavioral testing and remediation platform for AI agents and models.


AI Control Plane monitors, evaluates, and governs enterprise AI agents across their lifecycle.




Platform that discovers, monitors, and governs enterprise AI agents at runtime.


AgentShield is an AI agent security control layer that inspects and governs agent traffic in the request and action path.


Amazon Bedrock Guardrails is a configurable safeguard layer that evaluates and filters inputs and outputs of generative AI applications.


Lightweight open classifier models that detect prompt injection and jailbreak attempts in LLM inputs.


Open-source toolkit for adding programmable guardrails to large language model applications.
Armadin's platform uses autonomous AI agents to validate exploitable enterprise attack paths.

MIND AI is the platform's AI data security analyst, monitoring data events, classifying sensitive data, and driving automated remediation.

Cisco AI Defense secures enterprise AI with asset discovery, model vulnerability evaluation, and runtime guardrails.

Autonomous AI penetration testing platform that continuously finds and validates exploitable vulnerabilities.

AI Red Teaming probes AI applications and agents for security and privacy risks via multi-turn attack simulation in CI/CD pipeline.

Pentera Platform is an automated security validation platform that emulates real attacker behavior across internal, cloud, and external environments.

AQtive Guard is an AI-powered platform that detects and remediates cryptographic and non-human identity vulnerabilities across enterprise IT.

Continuous behavioral testing and remediation platform for AI agents and models.

AI Control Plane monitors, evaluates, and governs enterprise AI agents across their lifecycle.

Arx is Fabraix's run-time defence layer that blocks prompt injection and memory poisoning in AI agents.

Security, safety, and reliability certification standard and technical evaluation suite for AI agents.

Platform that discovers, monitors, and governs enterprise AI agents at runtime.

AgentShield is an AI agent security control layer that inspects and governs agent traffic in the request and action path.

Amazon Bedrock Guardrails is a configurable safeguard layer that evaluates and filters inputs and outputs of generative AI applications.

Lightweight open classifier models that detect prompt injection and jailbreak attempts in LLM inputs.

Open-source toolkit for adding programmable guardrails to large language model applications.
