A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models

Name: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models
Uploaded: 2025-01-01
Duration: 29 min 28 s
Description: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models — a 2025 CAMLIS 2025 security conference talk on ai-ml, red-team (29:28 min). Watch the full video, indexed free on the Breach Arc Archive.

CAMLIS 2025 · 2025 · 29:28

▶

A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models — a 2025 CAMLIS 2025 security conference talk on ai-ml, red-team (29:28 min). Watch the full video, indexed free on the Breach Arc Archive.

▶ Watch video on YouTube

ai-ml red-team

← Back to the Breach Arc Archive