LLMs in a Hacker's Hands: From Prompt Injection to Data Leakage
summary
Examines how attackers can misuse large language models, covering prompt injection and data exfiltration techniques against LLMs. Focuses on practical cybersecurity issues and defensive awareness in using LLMs in hacker scenarios.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 2:33Prompt injection basics
- 11:25AI agent security
- 17:42LLMs in cyberattacks
- 32:10Malware-specialized models
- 37:26AI as attacker
- 42:13Summary
related talks
31mHacking with Words...
39mLLMs everywhere: The future is now and the past keeps repeating itself
44mI Abuse Your LLM Live with 10 Security Vulnerabilities
20mSecurity Threats in Modern LLM Applications
50mSecuring LLM-Powered Applications: Overcoming Security and Privacy Challenges
36mCompromising LLMs: The Advent of AI Malware
23mSecurity and auditing tools in Large Language Models (LLM)
47mHarnessing LLMs for Next-Level Security Analysis