LLM-Driven Attack Flow Generation from Security Publications
summary
The talk shows how generative AI and large language models can turn unstructured security publications into structured attack flows and threat intelligence. It describes automating attack-flow generation and integration of LLM-produced intelligence into SOC workflows to speed alert triage and enable more proactive defenses.
AI-written summary · about
chapters (6)
- 0:00Project introduction
- 9:23Data source processing
- 17:07Technical demo of flow
- 22:39Cybersecurity use cases
- 26:40Failures and future work
- 34:28Q&A
related talks
40mFrom Text to Flaws: Application Vulnerabilities with Generative AI and LLMs
47mHarnessing LLMs for Next-Level Security Analysis
43mLLMs in a Hacker's Hands: From Prompt Injection to Data Leakage
01mCombatting scalable AI attacks
39mThreat Modeling Using LLMs
40mFrom Text to Exploits: Vulnerabilities of Apps Using Generative AI and LLMs
46mFrom Text to Flaws: Vulnerabilities in Apps Using Generative AI and LLMs
31mHacking with Words...