Awesome-Info-Inferring-Binary

A collection of papers, tools about type inferring, variable renaming, and function name inferring on stripped binary executables.

Papers

| Paper | Venue | Year | Slide | Video | Source Code | Dataset | | :-------------: | :----------: | :--: | :-----------: | :--------------: | :---------------------: |:---------------------: | | RecStruct: Recovering Nested Struct Types from Stripped Binaries via Stack-Driven Unification | Usenix Sec | 2026 | S | V | RecStruct | RecStruct | | CiRCLE: Recovering Complex Data Structures in Binaries beyond Fragmentation | S&P | 2026 | S | V | CiRCLE | D | | HyRES: Recovering Data Structures in Binaries via SemanticEnhanced Hybrid Reasoning | TOSEM | 2026 | S | V | HyRES | D | | Beyond the Edge of Function: Unraveling the Patterns of Type Recovery in Binary Code| TOSEM | 2025 | S | V | ByteTR | D | | TypeForge: Synthesizing and Selecting Best-Fit Composite Data Types for Stripped Binaries | S&P | 2025 | S | V | TypeForge | TypeForge | TRex: Practical Type Reconstruction for Binary Code| Usenix Sec | 2025 | S | V | TRex | TRex| | BLens: Contrastive Captioning of Binary Functions using Ensemble Embedding| Usenix Sec | 2025 | S | V | Blens | Blens | | DecLLM LLM-Augmented Recompilable Decompilation for Enabling Programmatic Use of Decompiled Code | ISSTA | 2025 | S | V | DecLLM | D | |Unleashing the Power of Generative Model in Recovering Variable Names from Stripped Binary| NDSS | 2025 | S | V | Gennm | D | |Beyond Classification: Inferring Function Names in Stripped Binaries via Domain Adapted LLMs| NDSS | 2025 | S | V |SymGen | D | | DRAGON: Predicting Decompiled Variable Data Types with Learned Confidence Estimates | BAR 2025 (NDSS) | 2025 | S | V | G | D | |llasm: Naming Functions in Binaries by Fusing Encoder-only and Decoder-only LLMs | TOSEM | 2025 | S | V | llasm | D | | STRIDE: Simple Type Recognition In Decompiled Executables | ArXiv | 2024 | S | V | STRIDE | D | | ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries | CCS | 2024 | S | V | ReSym | D | | TYGR: Type Inference on Stripped Binaries using Graph Neural Networks | Usenix Sec | 2024 | S | V | TYGR |D | | Enhancing Function Name Prediction using Votes-Based Name Tokenization and Multi-task Learning | Proceedings of the ACM on Software EngineeringVolume 1, Issue FSE | 2024 | S | V | Epitome | D | | Ahoy SAILR! There is No Need to DREAM of C: A Compiler-Aware Structuring Algorithm for Binary Decompilation| Usenix Sec | 2024 | S | V | SAILR | D | | "Len or index or count, anything but v1": Predicting Variable Names in Decompilation Output with Transfer Learning| S&P | 2024 | S | V | VarBERT | D | | FunProbe: Probing Functions from Binary Code through Probabilistic Analysis | ESEC/FSE | 2023 | S | V | FunProbe | D | | CFG2VEC: Hierarchical Graph Neural Network for Cross-Architectural Software Reverse Engineering| ICSE | 2023| S | V | CFG2VEC | D | | A Transformer-based Function Symbol Name Inference Model from an Assembly Language for Binary Reversing | AsiaCCS | 2023 | S | V | AsmDepictor | D | | SymLM: Predicting Function Names in Stripped Binaries via Context-Sensitive Execution-Aware Code Embeddings | CCS | 2022 | S | V | SymLM | SymLM | | DnD: A Cross-Architecture Deep Neural Network Decompiler | Usenix Sec | 2022 | S | V | DnD | D | | DIRECT : A Transformer-based Model for Decompiled Variable Name Recovery | nlp4prog | 2021 | S | V | DIRECT-nlp4prog | D| | XFL: Naming Functions in Binaries with Extreme Multi-label Learning | S&P(Arxiv) | 2023(2021) | S | V | XFL | D | | Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling | Arxiv | 2021 | S | V | G | D | | DIRTY: Augmenting Decompiler Output with Learned Variable Names and Types | Usenix Sec | 2022 | S | V | DIRTY | Demo | D | | A Lightweight Framework for Function Name Reassignment Based on Large-Scale Stripped Binaries | ISSTA | 2021 | S | V | NFRE| D | | StateFormer: Fine-Grained Type Recovery from Binaries using Generative State Modeling | ESEC/FSE | 2021 | S | V | StateFormer | D | | OSPREY: Recovery of Variable and Data Structure via Probabilistic Analysis for Stripped Binary | S&P (Oakland) | 2021 | S | V | OSPREY| D | | Devil Is Virtual: Reversing Virtual Inheritance in C++ Binaries | CCS | 2020 | S | V | G | D | | Neural reverse engineering of stripped binaries using augmented control flow graphs| OOPLSA | 2020 | S | V| Nero | D | | CATI: Context-Assisted Type Inference from Stripped Binaries | DSN | 2020 | S | V | G | D | | Typilus: Neural Type Hints | PLDI | 2020 | S | V | Typilus | D | | In Nomine Function: Naming Functions in Stripped Binaries with Neural Networks| Arxiv | 2019 | S | V | in_nomine_function | D | | DIRE: A Neural Approach to Decompiled Identifier Naming | ASE | 2019 | S | V | Dire| D | | Type Learning for Binaries and its Applications | IEEETR | 2019 | S | V | BITY | D | | DeClassifier: Class-Inheritance Inference Engine for Optimized C++ Binaries | AsiaCCS | 2019 | S | V | DeClassifier | D | | DEBIN:Predicting Debug Information in Stripped Binaries | CCS | 2018 | S | V | DEBIN | debin.ai | D | | Meaningful variable names for decompiled code: a machine translation approach | ICPC | 2018 | S | V | G | D | | Neural Nets Can Learn Function Type Signatures From Binaries | Usenix Sec | 2017 | S | V | EKLAVYA | binary.tar.gz, [pickles.tar.gz](https://drive.google.com/file/d/0B2qBKMQRQLHGdGpuTUlmMmZJYXM/vie