20 results for “decompilers”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper introduces Decaf, a system that uses automatic feedback and search to significantly improve the semantic correctness and accuracy of neural decompilers, boosting the decompilation rate from…
This paper improves malware triage using large language models by providing both decompiler views.
The paper introduces SCDBench, a comprehensive benchmark dataset and methodology that rigorously evaluates LLM-based smart contract decompilers, finding that while frontier LLMs can generate compilabl…
The paper introduces SCDBench, a comprehensive benchmark dataset and methodology that rigorously evaluates LLM-based smart contract decompilers, finding that while frontier models can produce compilab…
The paper identifies issues with the ExeBench benchmark for evaluating LLM-based decompilers and proposes a revised version called ExeBench-FHD.
Puzhuo Liu, Yuhan Huang, Jianlei Chi, Peng Di +1 more
The paper introduces DEBENCH, a novel framework that evaluates binary decompilers based on three orthogonal dimensions—readability, recompilability, and functionality—revealing that functional recover…
The paper introduces VulDec, a framework for binary vulnerability detection using neural decompilation.
This paper proposes a novel decompiler-based approach called VMSpec to automate the construction of VM processor specifications, enabling existing decompilers to analyze VM-obfuscated code.
Han Dai, Soumyakant Priyadarshan, Abdullah Imran, Ruoyu Wang +1 more
SCRIBE is a novel framework that enables reliable source-level patching of binaries by performing 'binary-aware' recompilation, successfully resolving syntactic and semantic inaccuracies inherent in d…
PUSHAN is a novel, trace-free technique that successfully deobfuscates virtualization-obfuscated binaries, providing complete Control Flow Graphs (CFGs) and high-quality C pseudocode for effective ana…
The paper proposes CoDe-R, a two-stage framework that significantly improves the accuracy and re-executability of decompiled code generated by LLMs, achieving a new SOTA in the lightweight regime.
Improves shared-library debloating by reconstructing libraries from file ranges
The paper introduces LLM4CodeRE, a domain-adaptive LLM framework that significantly improves bidirectional code reverse engineering by unifying assembly-to-source and source-to-assembly translation.
DecomposeRL introduces an accurate and traceable claim verification model by framing the decomposition process as an RL policy, achieving state-of-the-art performance with significantly fewer training…
MimeLens is a novel, position-agnostic BERT-style encoder that accurately detects file types from arbitrary binary fragments, outperforming existing methods like Magika, especially on non-standard inp…
The paper proposes a new binary format that embeds compiler-generated metadata into executables, making the binary structure more transparent and enabling reliable analysis, instrumentation, and recom…
This paper investigates prompt injection attacks targeting software reverse engineering AI agents, demonstrating detection and defense strategies against both direct and obfuscated attacks.
This paper investigates prompt injection attacks targeting software reverse engineering AI agents, demonstrating detection and defense strategies against both direct and obfuscated attacks.