Cybersecurity expert discusses threat modeling for LLM applications

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 1 source

This podcast episode features Donato from WithSecure discussing threat modeling for AI applications, specifically focusing on Large Language Models (LLMs). The conversation covers practical security aspects such as prompt injections, alignment issues, and the security canvas for LLM applications. It also touches on the risks of AI assistants and the potential for jailbreaking. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

RANK_REASON Podcast discussing practical AI security tools and techniques.

Read on Practical AI →

safety
other

Cybersecurity expert discusses threat modeling for LLM applications

COVERAGE [1]

Practical AI TIER_1 · Practical AI LLC · 2024-08-22 13:30

Threat modeling LLM apps

<p>If you have questions at the intersection of Cybersecurity and AI, you need to know Donato at WithSecure! Donato has been threat modeling AI applications and seriously applying those models in his day-to-day work. He joins us in this episode to discuss his LLM application secu…

COVERAGE [1]

Threat modeling LLM apps

RELATED TOPICS