MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation,...

How Malicious Android Apps Slip Into Disguise

Researchers say mobile malware purveyors have been abusing a bug in the Google Android platform that lets them sneak malicious code into mobile apps and evade security scanning tools. Google says it has updated its app malware detection mechanisms in response to the new research. At issue is a...

Semi-Automated Network Penetration Testing Framework: Legion

Legion, a fork of SECFORCE’s Sparta, is an open source, easy-to-use, super-extensible and semi-automated network penetration testing framework that aids in discovery, reconnaissance and exploitation of information systems. Legion is developed and maintained by GoVanguard. Features Automatic recon...