Okay Waymo, Crash My Car! 🗣️ Testing Autonomous Vehicle Safety with Adversarial Driving Scenarios...
Arian Abbasi
Okay Waymo, Crash My Car! 🗣️ Testing Autonomous Vehicle Safety with Adversarial Driving Scenarios...
18:16
The Full LLM Glossary and Foundations
Arian Abbasi
The Full LLM Glossary and Foundations
1:28:19
Anthropic's Best-of-N: Cracking Frontier AI Across Modalities
Arian Abbasi
Anthropic's Best-of-N: Cracking Frontier AI Across Modalities
12:38
Auto-Rewards & Multi-Step RL for Diverse AI Attacks by OpenAI
Arian Abbasi
Auto-Rewards & Multi-Step RL for Diverse AI Attacks by OpenAI
11:18
Battle of the Scanners: Top Red Teaming Frameworks for LLMs
Arian Abbasi
Battle of the Scanners: Top Red Teaming Frameworks for LLMs
14:48
Watermarking LLM Output: SynthID by DeepMind
Arian Abbasi
Watermarking LLM Output: SynthID by DeepMind
12:58
Open Source Red Teaming: PyRIT by Microsoft
Arian Abbasi
Open Source Red Teaming: PyRIT by Microsoft
10:54
Jailbreaking GPT o1: STCA Attack
Arian Abbasi
Jailbreaking GPT o1: STCA Attack
8:33
The Attack Atlas by IBM Research
Arian Abbasi
The Attack Atlas by IBM Research
11:15
The Single-Turn Crescendo Attack
Arian Abbasi
The Single-Turn Crescendo Attack
6:46
Outsmarting ChatGPT: The Power of Crescendo Attacks
Arian Abbasi
Outsmarting ChatGPT: The Power of Crescendo Attacks
9:50