AI Evaluation & Safety
HiddenLayer
HiddenLayer focuses on machine learning model security: detecting adversarial inputs, model theft, model tampering, and supply-chain attacks against ML pipelines. The company's Automated Red Teaming product runs adversarial probes against deployed models continuously, and the Model Scanner product inspects model artifacts for malicious code. HiddenLayer raised a $50M Series A in 2023 with M12 (Microsoft's venture fund) leading.
Why this matters in 2026
HiddenLayer research published in early 2024 demonstrated practical model-theft attacks against GPT-class models via the OpenAI API. The work directly shaped how foundation labs throttle and watermark inference responses.
Products
- HiddenLayer Model Scanner (artifact inspection)
- HiddenLayer AISec Platform (runtime detection)
- Automated Red Teaming
Primary focus
Model security: detecting adversarial attacks, model theft, and ML supply chain compromise
Applied AI roles HiddenLayer typically hires
DecipherU is not affiliated with, endorsed by, or sponsored by any company listed in this directory. Information compiled from publicly available sources for educational purposes.
Get cybersecurity career insights delivered weekly
Join cybersecurity professionals receiving weekly intelligence on threats, job market trends, salary data, and career growth strategies.
By subscribing you agree to our privacy policy. Unsubscribe anytime.