AI in Cybersecurity: Offense and Defense
summary
The talk examines how large language models like ChatGPT and Google Gemini affect cybersecurity, showing how attackers can misuse them for offensive techniques such as social engineering and outlining the associated security risks. It also reviews defensive strategies and practical measures to protect information against AI-enabled threats, presenting a comprehensive view of AI’s capabilities and challenges in cyber defense.
AI-written summary · about
chapters (17)
- 0:00Introduction
- 0:28Agenda
- 1:12AI history
- 3:00Neural networks
- 4:03LLMs explained
- 6:54LLM tokens and parameters
- 8:18LLM temperature and fine-tuning
- 11:25Red Team vs Blue Team
- 12:50Prompt injection attacks
- 13:10LLM jailbreaks
- 14:13ASKI attacks
- 14:56WormGPT threats
- 15:18Public GPT vulnerabilities
- 17:23LLM viruses like Morris 2
- 18:28Cybersecurity defense strategies
- 21:38AI and cybersecurity conclusions
- 23:49Q&A
related talks
53mHow AI is impacting cybersecurity. Does it?
01h 24mOffensive Cybersecurity by AI Promises and Pitfalls
49mThe Intersection of AI and Cybersecurity
49mGenAI and Cybersecurity: Safeguarding the Digital Age
07mCybersecurity Analysts' Perception of AI Security Tools and Practical Implications
27mUse AI to Boost Your Company's Security
18mDefending the unknown using AI and cybersecurity
41mAI and cyber, or why your vacuum cleaner (still)...