News
AutoDFBench 1.0: A Benchmarking Framework for Digital Forensic Tool Testing and Generated Code Evaluation
Congratulations to Akila Wickramasekara and co-authors Tharusha Mihiranga, Aruna Withanage, Buddhima Weerasinghe, Frank Breitinger, John Sheppard, and Mark Scanlon on the publication of AutoDFBench 1.0: A Benchmarking Framework for Digital Forensic Tool Testing and Generated Code Evaluation in Forensic Science International: Digital Investigation.
Co-authors: Tharusha Mihiranga, Aruna Withanage, Buddhima Weerasinghe, Frank Breitinger, John Sheppard, and Mark Scanlon.
AI-generated summary of the contribution: AutoDFBench 1.0 is a modular benchmarking framework that supports the evaluation of both conventional digital forensic tools and scripts, as well as AI-generated code and agentic approaches. It integrates five areas defined by the NIST Computer Forensics Tool Testing (CFTT) programme: string search, deleted file recovery, file carving, Windows registry recovery, and SQLite data recovery. The framework includes ground truth data comprising 63 test cases and 10,968 unique test scenarios, and executes evaluations through a RESTful API that produces structured JSON outputs with standardised metrics. AutoDFBench 1.0 enables fair and reproducible comparison across tools and forensic scripts, establishing the first unified, automated, and extensible benchmarking framework for digital forensic tool testing and validation.