The HiddenLayer ML Model Scanner will be integrated with Intel's Confidential Computing powered by Intel Software Guard Extensions (Intel SGX)

AUSTIN, Texas, April 20, 2023 /PRNewswire/ -- HiddenLayer, a Gartner recognized AI Application Security company, is proud to announce a strategic collaboration with Intel Corporation to deliver a comprehensive hardware and software-based ML security solution for organizations in regulated and compliance-focused industries.

Recognizing the current gap in ML scanning within a secure environment, Intel and HiddenLayer have come together to offer customers an end-to-end ML model protection platform. This technology collaboration leverages the scale, performance, and privacy of Confidential Computing, built with HiddenLayer's cutting-edge adversarial ML threat protection capabilities and Intel SGX.

Customers can now access an encrypted ML Model Scanner designed to protect their ML models. Intel SGX enables the smallest trust boundary for Confidential Computing. It's the most researched, updated, and deployed confidential computing technology in the data center on the market today. This is critical for driving the continued adoption of AI across industries.

HiddenLayer, with support from Intel, is committed to building one of the industry's most secure ML model integrity platforms. By running the HiddenLayer Model Scanner in a Trusted Execution Environment (TEE), customers can help safeguard their most valuable intellectual property: their AI.

The HiddenLayer ML Model Scanner delivers:

• Malware Analysis: Scans ML models for embedded malicious code that could serve as an infection vector and launchpad for malware.
• Vulnerability Assessment: Scans for known CVEs and zero-day vulnerabilities targeting ML models.
• Model Integrity: Analysis of ML model's layers, components, and tensors to detect tampering or corruption.
• Comprehensive Detection: Utilizes a combination of static detection, dynamic analysis, and machine learning techniques to identify malware, vulnerabilities, model integrity, and corruption issues.
• Catalog a Known-Good State: Baseline your ML models for identifying future tampering.

Broad Support: Supports various ML model file types, including Pickle, Dill, Joblib, Numpy, Zip, ONNX, and HDF5.

Intel's commitment to cybersecurity is evident in its extensive Confidential Computing portfolio. Confidential Computing powered by Intel SGX offers a TEE to help protect sensitive data.

Industries with strict regulatory and compliance requirements can significantly benefit from Confidential Computing. Intel SGX is continuously improved over time, with deployments across major cloud service providers including IBM, Alibaba, Baidu, and Microsoft.

"We are excited to collaborate with Intel, a global technology leader, to offer our customers the most secure and comprehensive ML security solution on the market," said Christopher "Tito" Sestito, Co-founder and CEO at HiddenLayer. "This collaboration strengthens our commitment to protecting organizations' AI assets and paves the way for broader AI adoption across industries. Building on Intel technology, we are revolutionizing how businesses approach ML model security, ensuring the integrity and safety of their most valuable intellectual property."

"At Intel, we understand the importance of securing the rapidly evolving landscape of AI and machine learning. Our collaboration with HiddenLayer represents a significant step forward in delivering a robust end-to-end ML security solution for organizations in regulated and compliance-focused industries. By combining Confidential Computing on Intel SGX with HiddenLayer's innovative ML Model Scanner, we can empower businesses to better protect their AI assets with confidence, while fostering continued adoption and innovation in AI," said Rick Echevarria, Vice President, Sales and Marketing Group, General Manager for Security at Intel.

Plans for the collaboration include the continued technical integration of the HiddenLayer MLDR product with Intel SGX. Additionally, joint research, channel activation, customer education, and enablement will be key focus areas in the go-to-market strategy.

HiddenLayer, one of 10 finalists for the RSA Conference™ 2023 Innovation Sandbox contest, will present its MLSecurity Platform to a panel of renowned industry judges and a live in-person audience on Monday, April 24th, at RSA. For more information regarding RSA Conference 2023 at the Moscone Center in San Francisco from April 24-27, please visit https://www.rsaconference.com/usa.

Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries.

About HiddenLayer

HiddenLayer, a Gartner-recognized AI Application Security company, helps enterprises safeguard the machine learning models behind their most important products with a comprehensive security platform. Only HiddenLayer offers turnkey AI/ML security that does not add unnecessary complexity to models and does not require access to raw data and algorithms. Founded in March of 2022 by experienced security and ML professionals, HiddenLayer is based in Austin, Texas, and is backed by cybersecurity investment specialist firm Ten Eleven Ventures. For additional information, including product and the latest research reports, visit www.hiddenlayer.com.

Media Contact:
Rachel Kaseroff
Rachel@RJKCommunications.net 
(415) 341-5625

SOURCE HiddenLayer