Rethinking Neural Decompilation: Candidate Selection as the Hidden Bottleneck
cs.CR, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/jgamblin/Mirai-Source-Code
Terminology
Sources
- HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation
- Evaluating Large Language Models Trained on Code
- Towards Neural Decompilation
- Competition-Level Code Generation with AlphaCode
- The CodeInverter Suite: Structure- and Data-Aware Binary Decompilation with Efficient LLMs
- A Comprehensive Evaluation of Code Language Models for Security Patch Detection
- Beyond Accuracy: Characterizing Code Comprehension Capabilities in (Large) Language Models
- CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
- Deconstructing Obfuscation: A four-dimensional framework for evaluating Large Language Models assembly code deobfuscation capabilities
- SALT4Decompile: Inferring Source-level Abstract Logic Tree for LLM-Based Binary Decompilation
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data