Generative AI-based applications have the most business impact when they have access to critical business data and are empowered to take actions on behalf of the user. However, these integrations raise important security questions outlined in the OWASP Top 10 for LLM vulnerabilities and NIST Adversarial Machine Learning frameworks. This lightning talk introduces high-level architectural patterns to effectively mitigate key OWASP Top 10 for LLM vulnerabilities through Zero Trust principles. Leave this talk with best practices for building generative AI applications accessing sensitive business data using Agents for Amazon Bedrock.
Learn more about AWS re:Inforce at go.aws/reinforce.
Subscribe:
More AWS videos: bit.ly/2O3zS75
More AWS events videos: bit.ly/316g9t4
ABOUT AWS
Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts.
AWS is the world's most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers-including the fastest-growing startups, largest enterprises, and leading government agencies-are using AWS to lower costs, become more agile, and innovate faster.
#reInforce2024 #CloudSecurity #AWS #AmazonWebServices #CloudComputing
Негізгі бет Ғылым және технология AWS re:Inforce 2024 - Mitigate OWASP Top 10 for LLM risks with a Zero Trust approach (GAI323)
Пікірлер