STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation

• URL: http://arxiv.org/abs/2608.26408v1
• Date: Wed, 26 Aug 2026 21:20:54 GMT
• Title: STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation
• Abstract summary: We present STILL, a structured semantic interface that predicts function-level STL container semantics from stripped control-flow graphs.<n>On StlBench, STILL predicts common container-level STL semantics, with the strongest cross-dataset results for stable string and vector slices.<n>On stripped HumanEval decompilation, these hints enable DeepSeek-chat refinement to reach 28.4% executability, compared with 17.4% for no-hint refinement.
• Score: 51.12395225250876
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: LLM-assisted decompilation improves readability and re-executability, but still underperforms on stripped C++ functions that use the Standard Template Library (STL). Compilation, optimization, and symbol stripping remove or obscure source-level semantics such as container types and library-call structure, while traditional decompiler output often fails to recover them. We present STILL, a structured semantic interface that predicts function-level STL container semantics from stripped control-flow graphs and renders them as compact hints for LLM refinement. On StlBench, STILL predicts common container-level STL semantics, with the strongest cross-dataset results for stable string and vector slices. On stripped HumanEval decompilation, these hints enable DeepSeek-chat refinement to reach 28.4% executability, compared with 17.4% for no-hint refinement and 8.9% for raw Ghidra decompilation; hint utility is downstream-backbone-dependent, with decompilation-specialized models requiring lightweight adaptation to benefit from the same interface.

Related papers

• Portable models as a replacement for industrial heuristics in compiler optimizations [0.0]
  The paper investigates the possibility of predicting function-inlining decisions in compact compilers, source-to-source tools, and interpreters.<n>The relevance of this work is determined by the need to transfer mature inlining optimizations to systems with limited compiler infrastructure.
  arXiv  Detail & Related papers  (2026-07-19T19:43:14Z)
• HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation [11.110675371854988]
  textscHELIOS is a framework that reframes binary decompilation as a structured reasoning task.<n>textscHELIOS is a practical building block for reverse engineering in security settings.
  arXiv  Detail & Related papers  (2026-01-21T02:37:33Z)
• Multi-Agent Taint Specification Extraction for Vulnerability Detection [49.27772068704498]
  Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results.<n>We present SemTaint, a multi-agent system that strategically combines the semantic understanding of Large Language Models (LLMs) with traditional static program analysis.<n>We integrate SemTaint with CodeQL, a state-of-the-art SAST tool, and demonstrate its effectiveness by detecting 106 of 162 vulnerabilities previously undetectable by CodeQL.
  arXiv  Detail & Related papers  (2026-01-15T21:31:51Z)
• TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization [52.01940078632388]
  We introduce TASO, a novel jailbreak method that optimize both a template and a suffix in an alternating manner.<n>We evaluate the effectiveness of TASO on benchmark datasets on 24 leading LLMs.
  arXiv  Detail & Related papers  (2025-11-23T18:49:27Z)
• Context-Guided Decompilation: A Step Towards Re-executability [50.71992919223209]
  Binary decompilation plays an important role in software security analysis, reverse engineering and malware understanding.<n>Recent advances in large language models (LLMs) have enabled neural decompilation, but the generated code is typically only semantically plausible.<n>We propose ICL4Decomp, a hybrid decompilation framework that leverages in-context learning (ICL) to guide LLMs toward generating re-executable source code.
  arXiv  Detail & Related papers  (2025-11-03T17:21:39Z)
• TIT: A Tree-Structured Instruction Tuning Approach for LLM-Based Code Translation [11.882496324328905]
  We propose TIT, a Tree-structured Instruction Tuning paradigm for LLM-based code translation.<n>To mitigate syntactic confusion, the syntactic information representation module integrates language-agnostic syntactic features.<n>To generate high-quality fine-grained parallel data, the fine-grained parallel dataset augmentation module aligns nodes with code segments.
  arXiv  Detail & Related papers  (2025-10-10T13:53:46Z)
• D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning [49.16469288280772]
  Decompilers reconstruct human-readable source code from binaries.<n>Despite recent advances, their outputs often suffer from syntactic and semantic errors and remain difficult to read.<n>With the advent of large language models (LLMs), researchers began to explore the potential of LLMs to refine decompiler output.<n>We present D-LIFT, an enhanced decompiler-LLM pipeline with fine-tuned reinforcement learning.
  arXiv  Detail & Related papers  (2025-06-11T19:09:08Z)
• VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations [17.974013479973774]
  VecTrans is a framework that leverages large language models to enhance compiler-based code vectorization.<n>VecTrans achieves an geomean speedup of 1.77x and successfully vectorizes 24 of 51 test cases.
  arXiv  Detail & Related papers  (2025-03-25T08:39:35Z)
• ReF Decompile: Relabeling and Function Call Enhanced Decompile [50.86228893636785]
  The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages.<n>This task supports various reverse engineering applications, such as vulnerability identification, malware analysis, and legacy software migration.
  arXiv  Detail & Related papers  (2025-02-17T12:38:57Z)
• LLM-Vectorizer: LLM-based Verified Loop Vectorizer [12.048697450464935]
  Large-language models (LLMs) can generate vectorized code from scalar programs that process individual array elements. LLMs are capable of producing high performance vectorized code with run-time speedup ranging from 1.1x to 9.4x. Our approach is able to verify 38.2% of vectorizations as correct on the TSVC benchmark dataset.
  arXiv  Detail & Related papers  (2024-06-07T07:04:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.