Lucene search
K

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

🗓️ 11 Mar 2026 00:00:00Reported by Yitian Qian, Yuan Tang, Youting Wang, Chen ZhaoType 
packetstormnews
 packetstormnews
🔗 packetstorm.news👁 8 Views

VisualLeakBench screens LVLMs for PII leakage and social engineering via OCR injection on synthetic and real-world images.

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