Lucene search
K

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

🗓️ 08 Jun 2025 00:00:00Reported by Yepang Liu, Zhen Sun, Zhiyuan Zhong, Xinlei He, Guanhong TaoType 
packetstormnews
 packetstormnews
🔗 packetstorm.news👁 3 Views

BadSem poisons vision-language models via semantic mismatches; SIMBad enables poisoning.

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

08 Jun 2025 00:00Current
6.9Medium risk
Vulners AI Score6.9
3