@inproceedings{10.1145/3465413.3488575,
author = {Weideman, Nicolaas and Felkner, Virginia K. and Wu, Wei-Cheng and May, Jonathan and Hauser, Christophe and Garcia, Luis},
title = {PERFUME: Programmatic Extraction and Refinement for Usability of Mathematical Expression},
year = {2021},
isbn = {9781450385527},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3465413.3488575},
doi = {10.1145/3465413.3488575},
abstract = {Algorithmic identification is the crux for several binary analysis applications, including malware analysis, vulnerability discovery, and embedded firmware reverse engineering. However, data-driven and signature-based approaches often break down when encountering outlier realizations of a particular algorithm. Moreover, reverse engineering of domain-specific binaries often requires collaborative analysis between reverse engineers and domain experts. Communicating the behavior of an unidentified binary program to non-reverse engineers necessitates the recovery of algorithmic semantics in a human-digestible form. This paper presents PERFUME, a framework that extracts symbolic math expressions from low-level binary representations of an algorithm. PERFUME works by translating a symbolic output representation of a binary function to a high-level mathematical expression. In particular, we detail how source and target representations are generated for training a machine translation model. We integrate PERFUME as a plug-in for Ghidra--an open-source reverse engineering framework. We present our preliminary findings for domain-specific use cases and formalize open challenges in mathematical expression extraction from algorithmic implementations.},
booktitle = {Proceedings of the 2021 Research on Offensive and Defensive Techniques in the Context of Man At The End (MATE) Attacks},
pages = {59–69},
numpages = {11},
keywords = {reverse engineering, binary analysis},
location = {Virtual Event, Republic of Korea},
series = {Checkmate '21}
}

{"_id":"a4KwPpoJ73wEA7bax","bibbaseid":"weideman-felkner-wu-may-hauser-garcia-perfumeprogrammaticextractionandrefinementforusabilityofmathematicalexpression-2021","author_short":["Weideman, N.","Felkner, V. K.","Wu, W.","May, J.","Hauser, C.","Garcia, L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Weideman"],"firstnames":["Nicolaas"],"suffixes":[]},{"propositions":[],"lastnames":["Felkner"],"firstnames":["Virginia","K."],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Wei-Cheng"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Hauser"],"firstnames":["Christophe"],"suffixes":[]},{"propositions":[],"lastnames":["Garcia"],"firstnames":["Luis"],"suffixes":[]}],"title":"PERFUME: Programmatic Extraction and Refinement for Usability of Mathematical Expression","year":"2021","isbn":"9781450385527","publisher":"Association for Computing Machinery","address":"New York, NY, USA","url":"https://doi.org/10.1145/3465413.3488575","doi":"10.1145/3465413.3488575","abstract":"Algorithmic identification is the crux for several binary analysis applications, including malware analysis, vulnerability discovery, and embedded firmware reverse engineering. However, data-driven and signature-based approaches often break down when encountering outlier realizations of a particular algorithm. Moreover, reverse engineering of domain-specific binaries often requires collaborative analysis between reverse engineers and domain experts. Communicating the behavior of an unidentified binary program to non-reverse engineers necessitates the recovery of algorithmic semantics in a human-digestible form. This paper presents PERFUME, a framework that extracts symbolic math expressions from low-level binary representations of an algorithm. PERFUME works by translating a symbolic output representation of a binary function to a high-level mathematical expression. In particular, we detail how source and target representations are generated for training a machine translation model. We integrate PERFUME as a plug-in for Ghidra–an open-source reverse engineering framework. We present our preliminary findings for domain-specific use cases and formalize open challenges in mathematical expression extraction from algorithmic implementations.","booktitle":"Proceedings of the 2021 Research on Offensive and Defensive Techniques in the Context of Man At The End (MATE) Attacks","pages":"59–69","numpages":"11","keywords":"reverse engineering, binary analysis","location":"Virtual Event, Republic of Korea","series":"Checkmate '21","bibtex":"@inproceedings{10.1145/3465413.3488575,\nauthor = {Weideman, Nicolaas and Felkner, Virginia K. and Wu, Wei-Cheng and May, Jonathan and Hauser, Christophe and Garcia, Luis},\ntitle = {PERFUME: Programmatic Extraction and Refinement for Usability of Mathematical Expression},\nyear = {2021},\nisbn = {9781450385527},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nurl = {https://doi.org/10.1145/3465413.3488575},\ndoi = {10.1145/3465413.3488575},\nabstract = {Algorithmic identification is the crux for several binary analysis applications, including malware analysis, vulnerability discovery, and embedded firmware reverse engineering. However, data-driven and signature-based approaches often break down when encountering outlier realizations of a particular algorithm. Moreover, reverse engineering of domain-specific binaries often requires collaborative analysis between reverse engineers and domain experts. Communicating the behavior of an unidentified binary program to non-reverse engineers necessitates the recovery of algorithmic semantics in a human-digestible form. This paper presents PERFUME, a framework that extracts symbolic math expressions from low-level binary representations of an algorithm. PERFUME works by translating a symbolic output representation of a binary function to a high-level mathematical expression. In particular, we detail how source and target representations are generated for training a machine translation model. We integrate PERFUME as a plug-in for Ghidra--an open-source reverse engineering framework. We present our preliminary findings for domain-specific use cases and formalize open challenges in mathematical expression extraction from algorithmic implementations.},\nbooktitle = {Proceedings of the 2021 Research on Offensive and Defensive Techniques in the Context of Man At The End (MATE) Attacks},\npages = {59–69},\nnumpages = {11},\nkeywords = {reverse engineering, binary analysis},\nlocation = {Virtual Event, Republic of Korea},\nseries = {Checkmate '21}\n}\n\n\n\n\n","author_short":["Weideman, N.","Felkner, V. K.","Wu, W.","May, J.","Hauser, C.","Garcia, L."],"key":"10.1145/3465413.3488575","id":"10.1145/3465413.3488575","bibbaseid":"weideman-felkner-wu-may-hauser-garcia-perfumeprogrammaticextractionandrefinementforusabilityofmathematicalexpression-2021","role":"author","urls":{"Paper":"https://doi.org/10.1145/3465413.3488575"},"keyword":["reverse engineering","binary analysis"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://jonmay.github.io/webpage/cutelabname/cutelabname.bib","dataSources":["YtBDXPDiQEyhyEDZC","ntRmLzdBaoXbDrD8C","hbZSwot2msWk92m5B","y8Du94SQQE4osp3cR","YWgSDDpCXg94hahkt","nZpECqBHtcWYeRmxt","BnZgtH7HDESgbxKxt","fcWjcoAgajPvXWcp7","GvHfaAWP6AfN6oLQE","fhHfrQgj3AaGp7e9E","qzbMjEJf5d9Lk78vE","45tA9RFoXA9XeH4MM","MeSgs2KDKZo3bEbxH","nSXCrcahhCNfzvXEY","ecatNAsyr4f2iQyGq","tpWeaaCgFjPTYCjg3","j3Qzx9HAAC6WtJDHS","5eM3sAccSEpjSDHHQ"],"keywords":["reverse engineering","binary analysis"],"search_terms":["perfume","programmatic","extraction","refinement","usability","mathematical","expression","weideman","felkner","wu","may","hauser","garcia"],"title":"PERFUME: Programmatic Extraction and Refinement for Usability of Mathematical Expression","year":2021}