Generative Email Attacks and How to Defend Against Them
summary
Describes how modern large language models can be used to craft convincing phishing and social-engineering emails and explores defensive measures security teams can adopt. Covers the capabilities of current text-generation technologies and practical preparation strategies for defending against generative email and social attacks.
AI-written summary · about
chapters (14)
- 0:00Start
- 1:33Why is email security important?
- 2:29Language in Business Email Compromise
- 6:08General Purpose Text Generation using GPT-3
- 8:15How to Control a Billion Parameter Model
- 13:38Personalized Spear Phishing Attacks
- 17:23Failure Case of Generation
- 18:10Personalized Social Engineering
- 21:26GPT-3 Bio Generation
- 23:37Prompt for Question Generation
- 25:31Limitations - Context Window
- 33:30GPT-3 for dataset augmentation
- 34:16Code Generation From Prompt
- 38:59Protect
related talks
46mGenerative AI: Cyber resiliency and risk
01mCombatting scalable AI attacks
17mWhat You Need to Know and How to Respond to the New Wave of GenAI Identity Attacks
40mFrom Text to Exploits: Vulnerabilities of Apps Using Generative AI and LLMs
46mHow to Tame Your Dragon: Productionizing Agentic...
27mSafeguarding Generative AI Applications: Navigating Security Challenges and Best Pract...
40mFrom Text to Flaws: Application Vulnerabilities with Generative AI and LLMs
27mAl-Generated Attacks: The New Era of Threats to Authentication