Lakera has been recognized in a report from NIST (National Institute of Standards and Technology) titled "Adversarial Machine Learning - A Taxonomy and Terminology of Attacks and Mitigations."
The report explores adversarial machine learning, focusing on the classification of attacks and strategies for their mitigation.
Lakera’s solutions are noted in the context of defending LLMs against prompt injection attacks, which highlights the effectiveness of our detection techniques in identifying and mitigating potential security risks.
This acknowledgment by NIST is significant for us. Not only does it validate our work but also highlights the need for strong AI security.
The report itself is a valuable resource for professionals working to secure AI systems, offering a comprehensive overview of the challenges and solutions related to adversarial machine learning.
