LLMs at the Core: From Attention to Action in...
summary
Open-sourced tools automate SDLC reviews, access requests and bug‑bounty triage: a Slack SDLC bot scans design docs and raised a risk score from 4 to 7 when private links were removed; an access manager suggests groups, files approval requests and issues time‑limited grants; a triage bot sorted 900+ daily bug reports, helped close ~3,500 invalid tickets and surfaced 32 real fixes in week one. Models self‑grade with evals, human review stays in the loop and IR bots prompt users to revert accidental public shares.
AI-written summary · about
chapters (9)
- 0:00Introduction and origin
- 2:47LLM security foundations
- 6:12SDLC security automation
- 11:38Security triage automation
- 13:44Access management tools
- 16:08Bug bounty program triage
- 22:56Incident response automation
- 26:03Final lessons and takeaways
- 27:14Q&A session
related talks
33mAgent-Based LLMs for Data Analysis and Fixing Software Bugs
26mHow Bad Actors AbUse LLMs The Mechanisms That Enable Misuse and What We Can Do About
19mEveryday AI: Leveraging LLMs for Simple...
19mTesting LLM-Powered Applications
42mHuman in the loop is not enough
48mBeyond the Prompt: Evaluating, Testing, and Securing LLM Applications
01h 49mAI engineering with open access LLMs that lie, curse, and steal
17mArchitecting LLM-Based Chatbots using free open-source LLMs