#AIOps
#MLSecOps
"WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents", 2025.
]-> Comprehensive benchmark for prompt injection detection in web agents
// we presenting the first comprehensive benchmark study on detecting prompt injection attacks targeting web agents. We construct datasets containing both malicious and benign samples: malicious text segments generated by different attacks, benign text segments from four categories, malicious images produced by attacks, and benign images from two categories
Post #1619
170