HiddenLayer has launched its flagship product, which is a security platform built to detect and prevent cyberattacks that target machine-learning-powered systems, following a stealth period.
The company claims its product is the industry’s first and only machine larning detection and response solution that protects enterprises and their customers from their emerging attack vector.
Hidden Layer claims its MLDR solution uses a ML-based approach to analyse billions of model interactions per minute to identify malicious activity without any access to or prior knowledge of the user’s ML model(s) or sensitive training data. It detects and responds to attack against ML models to protect IP and trade secrets from theft or tampering and ensure users are not exposed to attacks.
The firm said, “HiddenLayer’s MLDR is a non-invasive and easy-to-use security solution that does not require access to raw data or algorithms. It identifies patterns in ML model traffic through contextless vectorised data points to provide comprehensive defense from adversarial attacks targeting the deployed ML model in production.
Alongside the product launch, the company also raised $6m in a seed funding round headed by Ten Eleven Ventures.
HiddenLayer CEO Chris Sestito added, “We led the relief effort after our machine learning model was attacked directly through our product, and realized this would be an enormous problem for any organisation deploying ML models in their products. We decided to found HiddenLayer to both educate enterprises about this significant threat and help them defend against it.”
Copyright © 2022 RegTech Analyst
Copyright © 2018 RegTech Analyst