Lucene search
K

Hijacking Large Language Models Via Adversarial In-Context Learning

🗓️ 29 May 2025 00:00:00Reported by Xiangyu Zhou, Dongxiao Zhu, Saleh Zare Zade, Yao Qiang, Prashant KhanduriType 
packetstormnews
 packetstormnews
🔗 packetstorm.news👁 3 Views

Proposes a transferable prompt injection attack on in-context learning with imperceptible suffixes and defenses.

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