Search Results for author:
Found 2 papers, 1 papers with code
When Dataflow Analysis Meets Large Language Models
Dataflow analysis is a powerful code analysis technique that reasons dependencies between program values, offering support for code optimization, program comprehension, and bug detection.
Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications
To this end, we propose DFLARE, a novel, search-based, black-box testing technique to automatically find triggering inputs that result in deviated behaviors in image classification tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
