Hacking with Words...
summary
Explores vulnerabilities in large language models (LLMs) by demonstrating how crafted inputs can exploit weaknesses; discusses specific attack techniques and their effects on model behavior, likely referencing common LLM architectures and prompt-based methods; presents mitigation strategies and practical considerations for securing LLM deployments.
AI-written summary · about
related talks
43mLLMs in a Hacker's Hands: From Prompt Injection to Data Leakage
23mSecurity and auditing tools in Large Language Models (LLM)
44mI Abuse Your LLM Live with 10 Security Vulnerabilities
47mCurrent Security Threats in Large Language Model Applications
40mFrom Text to Flaws: Application Vulnerabilities with Generative AI and LLMs
47mA Step-by-Step Guide to Securing Large Language Models (LLMs)
46mHow Large Language Models Are Reshaping the Cybersecurity Landscape
40mFrom Text to Exploits: Vulnerabilities of Apps Using Generative AI and LLMs