Research question
How do LLMs help security, threaten it and suffer vulnerabilities?
Key findings
- Reviews LLMs for security tasks, LLM-enabled attacks and attacks on LLMs - Finds defensive uses outnumber offensive in the literature
A Survey on Large Language Model (LLM) Security and Privacy
A widely cited three-way survey of LLMs as security tools, as attack enablers and as targets.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.