Single-pass end-to-end neural decompilation using copying mechanism

• Published in: Neural computing & applications Vol. 37; no. 7; pp. 5309 - 5323
• Main Authors: Szalay, Gergő, Poór, Máté Bálint, Pintér, Balázs, Gregorics, Tibor
• Format: Journal Article
• Language: English
• Published: London Springer London 01.03.2025; Springer Nature B.V
• Subjects: Artificial Intelligence; Benchmarks; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer programming; Computer Science; Copying; Data Mining and Knowledge Discovery; Datasets; Deep learning; Error correction; Error correction & detection; Heuristic; Image Processing and Computer Vision; Neural networks; Original Article; Probability and Statistics in Computer Science; Programming languages; Variables; Decompilation; Single-pass; Seq2seq; End-to-end; Copying mechanism

Traditional decompilers utilize countless hardcoded rules written by subject matter experts, making them inflexible. Some recent systems address this using deep learning. The current consensus is that these systems have to include considerable domain knowledge and iterative heuristic components to s...