Vertical
Red Teaming within Safety & Evaluation.
13 listings
Applied AI and alignment research firm building custom ML models, AI agents, evals and red-teaming, with collaborators including DARPA and Anthropic.
Government and defense consultancy whose AI practice applies machine learning and adversarial-AI defenses to national security, civil and commercial missions.
MLOps & model tooling
CalypsoAI Moderator tests and protects language-model deployments through evaluation, filtering, and security controls.
MLOps & model tooling
Check Point AI Red Teaming tests generative AI applications for security vulnerabilities across models and prompts.
MLOps & model tooling
Giskard Hub continuously evaluates and red-teams AI agents for quality, hallucination, and security vulnerabilities.
MLOps & model tooling
Giskard OSS is an open-source Python library for testing model quality, bias, robustness, and LLM vulnerabilities.
MLOps & model tooling
HiddenLayer secures enterprise AI models through detection, monitoring, and adversarial threat defense.
iMerit offers multimodal data annotation, RLHF, model evaluation and red teaming through domain experts and its Ango Hub workflow platform, now part of EXL.
NCC Group is a UK cybersecurity consultancy with a Securing AI offering alongside CREST-accredited red teaming, assurance, incident response and managed services.
MLOps & model tooling
Protect AI Guardian scans AI systems for model, data, dependency, and runtime security risks.
MLOps & model tooling
Robust Intelligence AI Firewall validates model inputs and outputs to block attacks, errors, and unsafe behavior.
Trail of Bits provides security audits and research, including end-to-end AI/ML reviews of training data, MLOps pipelines, model artifacts and deployed agent loops.
MLOps & model tooling
Zscaler Automated AI Red Teaming continuously probes AI systems for unsafe behavior, attacks, and runtime exposure.
