Lucene search
+L

AutoRAN: Weak-To-Strong Jailbreaking of Large Reasoning Models

🗓️ 16 May 2025 00:00:00Reported by Ting Wang, Yuhui Wang, Jiacheng Liang, Rongyi Zhu, Fenglong Ma, Tanqiu JiangType 
packetstormnews
 packetstormnews
🔗 packetstorm.news👁 10 Views

AutoRAN automates weak-to-strong jailbreaking of large reasoning models by simulating reasoning with a weak model and refining prompts.

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation