arrow
Return

Identifying obfuscated code through graph-based semantic analysis of binary code

delete2025-09-30
delete0
delete
OA
AI
R
Roxane Cohen *
R
Robin David *
F
Florian Yger *
F
Fabrice Rossi *
DOI:10.1007/s41109-025-00733-8delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
Protecting sensitive program content is a critical concern in various situations, ranging from legitimate use cases to unethical contexts. Obfuscation is one of the most used techniques to ensure such a protection. Consequently, attackers must first detect and characterize obfuscation before launching any attack against it. This paper investigates the problem of function-level obfuscation detection using graph-based approaches, comparing algorithms, from classical baselines to advanced techniques like Graph Neural Networks (GNN), on different feature choices. We consider various obfuscation types and obfuscators, resulting in two complex datasets. Our findings demonstrate that GNNs need meaningful features that capture aspects of function semantics to outperform baselines. Our approach shows satisfactory results, especially in a challenging 11-class classification task and in two practical binary analysis examples. It highlights how much obfuscation and optimization are intertwined in binary code and that a better comprehension of these two principles are fundamental in order to obtain better detection results.
Keywords:
Obfuscation
Classification
GNN
Graphs
Graph representation learning
Security
Optimization

Journal

A
Applied Network Science
IF:
1.5
Papers:
65
Citations:
1.3K

Organization

C
centre national de la recherche scientifique (cnrs)
Scholars:
24.5W
Papers: 18.2W
Citations: 21.3W
U
universite de rouen normandie
Scholars:
121
Papers: 52
Citations: 3.3K
U
universite paris-dauphine
Scholars:
502
Papers: 482
Citations: 385
researcher View more organizations
Cited Papers

Cited Papers

Symbolic Deobfuscation: From Virtualized Code Back to the Original
err2018-06-08
err0
PREAI
errJonathan Salwan; Sébastien Bardin; Marie-Laure Potet
errShare
errSave
A survey on graph kernels
err2020-01-14
err0
errOAAI
errNils M. Kriege; Fredrik D. Johansson; Christopher Morris
errShare
errSave
Investigating Graph Embedding Neural Networks with Unsupervised Features Extraction for Binary Analysis
err2019-01-01
err0
errOAAI
errLuca Massarelli; Giuseppe A. Di Luna; Fabio Petroni; Leonardo Querzoni; Roberto Baldoni
errShare
errSave
A Generic Approach to Automatic Deobfuscation of Executable Code
err2015-05-01
err0
errOAAI
errBabak Yadegari; Brian Johannesmeyer; Ben Whitely; Saumya Debray
errShare
errSave
Defeating Opaque Predicates Statically through Machine Learning and Binary Analysis
err2019-11-15
err0
errOAAI
errRamtine Tofighi-Shirazi; Irina-Mariuca Asavoae; Philippe Elbaz-Vincent; Thanh-Ha Le
errShare
errSave
Fusion: measuring binary function similarity with code-specific embedding and order-sensitive gnn
err
IF0
err2022-12-02
err0
PREAI
errHao Gao; Tong Zhang; Songqiang Chen; Lina Wang; Fajiang Yu
errShare
errSave
Experimental Study of Binary Diffing Resilience on Obfuscated Programs
err2025-01-01
err0
PREAI
errCohen,Roxane; David,Robin; Mori,Riccardo; Yger,Florian; Rossi,Fabrice
errShare
errSave
researcher View more