Anthropic's Best-of-N: Cracking Frontier AI Across Modalities

About this episode

This episode explores the Best-of-N Jailbreaking algorithm and its implications for AI security and resilience.

In this special christmas episode, we delve into " Best-of-N Jailbreaking ," a powerful new black-box algorithm that demonstrates the vulnerabilities of cutting-edge AI systems. This approach works by sampling numerous augmented prompts - like shuffled or capitalized text - until a harmful response is elicited. Discover how Best-of-N (BoN) Jailbreaking achieves: 89% Attack Success Rates (ASR) on GPT-4o and 78% ASR on Claude 3.5 Sonnet with 10,000 prompts. Success in bypassing advanced defenses on both closed-source and open-source models. Cross-modality attacks on vision, audio, and multimodal AI systems like GPT-4o and Gemini 1.5 Pro. We’ll also explore how BoN Jailbreaking scales with the number of prompt samples, following a power-law relationship, and how combining BoN with other techniques amplifies its effectiveness. This episode unpacks the implications of these findings for AI security and resilience. Paper: Hughes, John, et al. " Best-of-N Jailbreaking ." (2024). arXiv . Disclaimer: This podcast summary was generated using Google's NotebookLM AI. While the summary aims to provide an overview, it is recommended to refer to the original research preprint for a…

People in this episode

Hosts: Arian Abbasi, Alan Aqrawi

Topics covered

• AI vulnerabilities
• black-box algorithms
• jailbreaking
• AI security
• cross-modality attacks

Keywords

• Best-of-N Jailbreaking
• AI vulnerabilities
• attack success rates
• cross-modality attacks
• GPT-4o
• Claude 3.5 Sonnet
• AI security

Mentioned in this episode

Organizations: GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro

Books & works: Best-of-N Jailbreaking

More episodes of AI Safety - Paper Digest

• AI Agents: Adoption and Usage | Perplexity Comet · December 10, 2025 · 5 min
• WEF & Accenture | Advancing Responsible AI Innovation: A Playbook · September 25, 2025 · 2 min
• Okay Waymo, Crash My Car! 🗣️ Testing Autonomous Vehicle Safety with Adversarial Driving Scenarios | LD-Scene · August 20, 2025 · 18 min
• The Full LLM Glossary and Foundations · August 4, 2025 · 1h 28m
• Auto-Rewards & Multi-Step RL for Diverse AI Attacks by OpenAI · November 30, 2024 · 11 min
• Battle of the Scanners: Top Red Teaming Frameworks for LLMs · November 4, 2024 · 15 min