#openworldwideapplicationsecurityproject — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #openworldwideapplicationsecurityproject, aggregated by home.social.
-
OWASP Top 10 for Large Language Model Applications
"The OWASP Top 10 for Large Language Model Applications project aims to educate developers, designers, architects, managers, and organizations about the potential security risks when deploying and managing Large Language Models (LLMs)."
https://owasp.org/www-project-top-10-for-large-language-model-applications/
Review the draft Top 10 list version 0.1: https://owasp.org/www-project-top-10-for-large-language-model-applications/descriptions/
1) Prompt Injections
2) Data Leakage
3) Inadequate Sandboxing
4) Unauthorized Code Execution
5) SSRF Vulnerabilities
6) Overreliance on LLM-generated Content
7) Inadequate AI Alignment
8) Insufficient Access Controls
9) Improper Error Handling
10) Training Data Poisoning
The initiative is community-driven, collaborate :)
#security #ai #data #llm #largelanguagemodel #artificialintelligence #owasp #training #OpenWorldwideApplicationSecurityProject #cybersecurity #community #owasptop10 #noprofit