In this work, we investigate the problem of revealing the functionality of a black-box agent. Notably, we are interested in the interpretable and formal description of the behavior of such an agent. Ideally, this description would take the form of a program written in a high-level language. This task is also known as reverse engineering and plays a pivotal role in software engineering, computer security, but also most recently in interpretability. In contrast to prior work, we do not rely on privileged information on the black box, but rather investigate the problem under a weaker assumption of having only access to inputs and outputs of the program. We approach this problem by iteratively refining a candidate set using a generative neural program synthesis approach until we arrive at a functionally equivalent program. We assess the performance of our approach on the Karel dataset. Our results show that the proposed approach outperforms the state-of-the-art on this challenge by finding a functional equivalent program in 78% of cases -- even exceeding prior work that had privileged information on the black-box.
History
Preferred Citation
Hossein Hajipour, Mateusz Malinowski and Mario Fritz. IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis. In: European Conference on Computer Vision (ECCV). 2020.
Primary Research Area
Trustworthy Information Processing
Name of Conference
European Conference on Computer Vision (ECCV)
Legacy Posted Date
2020-07-14
Open Access Type
Green
BibTeX
@inproceedings{cispa_all_3147,
title = "IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis",
author = "Hajipour, Hossein and Malinowski, Mateusz and Fritz, Mario",
booktitle="{European Conference on Computer Vision (ECCV)}",
year="2020",
}