Re:We fine-tuned an LLM to triage and fix insecure code
by asadeddin on Tuesday September 17, 2024 @12:31PM
(#41569486)
We completely agree. I would redefine it a bit.
We combine static analysis + LLMs to do better detection, triaging and auto-fixing because static analysis alone is broken in many ways.
We've been able to reduce ~30% of tickets for customers with false positive detection, and now be able to detect classes of vulnerabilities in business and code logic that were previously undetectable.
We combine static analysis + LLMs to do better detection, triaging and auto-fixing because static analysis alone is broken in many ways.
We've been able to reduce ~30% of tickets for customers with false positive detection, and now be able to detect classes of vulnerabilities in business and code logic that were previously undetectable.