No article text was recorded for this version.
semantic information loss
Version 2 of 2145 papers170 conceptsfrozen 2026-10-04
Papers in this version
- Blog: How Far Have We Gone in Binary Code Understanding Using Large Language Models
- Blog: Beyond Classification: Inferring Function Names in Stripped Binaries via Domain Adapted LLMs
- Blog: Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
- Blog: Refining Decompiled C Code with Large Language Models
- Blog: StackSight: Unveiling WebAssembly through Large Language Models and Neurosymbolic Chain-of-Thought Decompilation
- Blog: Estimating types in binaries using predictive modeling
- Blog: Semantic Understanding of Smart Contracts: Executable Operational Semantics of Solidity
- Blog: Neural reverse engineering of stripped binaries using augmented control flow graphs
- Blog: Code Action Network for Binary Function Scope Identification
- Blog: Topology-Inspired Method Recovers Obfuscated Term Information From Induced Software Call-Stacks
- Blog: There's Plenty of Room at the Bottom: Analyzing and Verifying Machine Code
- Blog: ECMO: Peripheral Transplantation to Rehost Embedded Linux Kernels
- Blog: Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models
- Blog: FoC: Figure Out the Cryptographic Functions in Stripped Binaries with LLMs
- Blog: An Automated Vulnerability Detection Framework for Smart Contracts
- Blog: CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision
- Blog: Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
- Blog: REMaQE: Reverse Engineering Math Equations from Executables
- Blog: LLM4Decompile: Decompiling Binary Code with Large Language Models
- Blog: Large Language Models for Code Analysis: Do LLMs Really Do Their Job?
- Blog: CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code
- Blog: Decompiling Smart Contracts with a Large Language Model
- Blog: MAD: Move AI Decompiler to Improve Transparency and Auditability on Non-Open-Source Blockchain Smart Contract
- Blog: MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization
- Blog: Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped Binary
- Blog: Cross-modal Retrieval Models for Stripped Binary Analysis
- Blog: Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement
- Blog: SigRec: Automatic Recovery of Function Signatures in Smart Contracts
- Blog: SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
- Blog: V-Fuzz: Vulnerability-Oriented Evolutionary Fuzzing
- Blog: DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
- Blog: NeuDep: neural binary memory dependence analysis
- Blog: How Far Have We Gone in Vulnerability Detection Using Large Language Models
- Blog: AMASS: Automated Software Mass Customization via Feature Identification and Tailoring
- Blog: Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients
- Blog: StoryDroid: Automated Generation of Storyboard for Android Apps
- Blog: On Benchmarking Code LLMs for Android Malware Analysis
- Blog: Binary Diff Summarization using Large Language Models
- Blog: Elysium: Automagically Healing Vulnerable Smart Contracts Using Context-Aware Patching
- Blog: FUSION: Measuring Binary Function Similarity with Code-Specific Embedding and Order-Sensitive GNN
- Blog: Mapping Modern JVM Language Code to Analysis-friendly Graphs: A Pilot Study with Kotlin
- Blog: SolidityCheck : Quickly Detecting Smart Contract Problems Through Regular Expressions
- Blog: CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code
- Blog: Pbaeg: combine-vulnerabilities AEG to defeat protection mechanisms
- Blog: Can We Run in Parallel? Automating Loop Parallelization for TornadoVM
- Blog: COMBO: Pre-Training Representations of Binary Code Using Contrastive Learning
- Blog: A Generating-Extension-Generator for Machine Code
- Blog: On the granularity of linguistic reuse
- Blog: Exploring the Feasibility of End-to-End Large Language Model as a Compiler
- Blog: A Multi-level Compiler Backend for Accelerated Micro-kernels Targeting RISC-V ISA Extensions
- Blog: LLM4Decompile: Decompiling Binary Code with Large Language Models
- Blog: ExVerus: Verus Proof Repair via Counterexample Reasoning
- Blog: How Far Have We Gone in Stripped Binary Code Understanding Using Large Language Models
- Blog: SigRec: Automatic Recovery of Function Signatures in Smart Contracts
- Blog: HEIR: A Unified Representation for Cross-Scheme Compilation of Fully Homomorphic Computation
- Blog: Recovery of Class Hierarchies and Composition Relationships from Machine Code
- Blog: MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation
- Blog: FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation
- Blog: Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection
- Blog: Poster: SigRec - Automatic Recovery of Function Signatures in Smart Contracts
Showing 60 of 145 papers.
History & citation
Current · Permanent link
- Neural Semantic Restoration for Binary Decompilation merged into this direction (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_semantic_information_loss_40b825ab,
title = {semantic information loss},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/semantic-information-loss/rdr_40b825abae5f4668960e85717b6cbf6c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_semantic_information_loss_40b825ab_v2,
title = {semantic information loss},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/semantic-information-loss/rdr_40b825abae5f4668960e85717b6cbf6c/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}