Lucene search
K

Secure Tug-Of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security

🗓️ 29 Jul 2025 00:00:00Reported by Junyu Gao, Hao Sun, Muzhi Dai, Xuelong Li, Zhiyuan Zhao, Shixuan LiuType 
packetstormnews
 packetstormnews
🔗 packetstorm.news👁 2 Views

SecTOW uses iterative defender and attacker training with reinforcement learning to improve multimodal model security against jailbreak inputs.

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

29 Jul 2025 00:00Current
7.2High risk
Vulners AI Score7.2
2