Lucene search
+L

ATOBench: Tracing How Autonomous Penetration-Testing Agents Verify Vulnerabilities When Target Evidence Lies

🗓️ 13 Aug 2026 00:00:00Reported by Qiyang Chen, Yixi Li, Junlin Liu, Fengwei ZhangType 
packetstormnews
 packetstormnews
🔗 packetstorm.news👁 3 Views

ATOBench is an evaluation framework that injects deceptive responses to probe how autonomous penetration-testing agents verify evidence and generate reports. It pairs transformed episodes with native ones and tracks recovery of proof, ownership, and artifacts.

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