arXiv AI September 17, 2026 By Jun Bi, Xiangxin Fang, Aarsh Chaube, Jos\'e Wesley De Souza Magalh\~aes, Rodrigo C. O. Rocha, Michael O'Boyle

Echo: Learning-based Matching Decompilation using Trusted Back Translation

Read the original on arXiv AI →

Echo is a matching decompilation system that uses trusted back‑translation to guide an iterative search for source code whose recompiled assembly exactly matches a target binary. It generates candidate programs and compilation configurations with a domain‑specific model, compiles them, measures assembly similarity, and refines mismatches through rule‑based, neural, and reasoning‑based techniques. In evaluations on function‑level benchmarks and the Mirai malware binary, Echo achieves 2.43× more exact matches than the strongest baseline and outperforms GPT‑5.6 and Codex by 2.75× and 7.4× on Mirai, respectively.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 19

Multi-View Decompilation for LLM-Based Malware Classification

arXiv:2606. 20436v1 Announce Type: cross Abstract: Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable.

By Bercan Turkmen, Vyas Raina

llms benchmarks

arXiv AI

Jul 13

REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming

arXiv:2607. 07738v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows.

By Nicolas Koller, Andreas u. Schmidt

llms benchmarks safety

arXiv AI

Jul 13

Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning

arXiv:2607. 09452v1 Announce Type: cross Abstract: We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning.

By Charles Edward Gagnon, Steven H. H. Ding, Philippe Charland, Benjamin C. M. Fung

llms

arXiv AI

Sep 7

When LLM Decompilers Recompile More and Preserve Less

The paper examines how large‑language‑model (LLM) decompilers, which produce clean, idiomatic C code, are currently evaluated mainly on recompilability and passing shipped tests. It shows that these metrics can mask significant behavioral differences: a decompiled function may recompile and pass all tests yet diverge on other inputs or lose disclosed vulnerabilities. To address this, the authors propose Decompile‑Diverge, a behavioral oracle that synthesizes drivers, fuzzes inputs, and compares the decompiled code’s behavior to the original, revealing divergences in up to 13% of cases and exposing gaps in current evaluation suites.

By Chang Liu, Edward Raff, Kristopher Micinski

llms

arXiv AI

Jul 13

Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity

arXiv:2509. 23449v2 Announce Type: replace Abstract: Binary code similarity detection is a core task in reverse engineering.

By Charles E. Gagnon, Steven H. H. Ding, Philippe Charland, Benjamin C. M. Fung

llms rag agents benchmarks safety

arXiv AI

Aug 13

Instruction Alignment for Binary Code Representation Learning

arXiv:2608. 11766v1 Announce Type: cross Abstract: Binary code representation learning is a fundamental problem in software security and reverse engineering.

By Huaijin Wang, Shuai Wang

rag safety

One email a morning, machine-written

Related stories

Multi-View Decompilation for LLM-Based Malware Classification

REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming

Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning

When LLM Decompilers Recompile More and Preserve Less

Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity

Instruction Alignment for Binary Code Representation Learning