Call Graph Context Improves Binary Embeddings But Lacks Generalization

A new research paper explores the impact of incorporating call graph context into binary function embedding models. The study found that while this inter-procedural context can improve robustness, particularly for namespace-related functions, improvements in one task like binary code similarity detection do not always generalize to other downstream tasks, such as those focused on syntactic similarity. The research suggests that optimizing for semantic similarity may lead to decreased performance on syntactic tasks. AI

IMPACT This research could lead to more robust and specialized binary analysis tools by understanding the trade-offs of using call graph context.

RANK_REASON The cluster contains a research paper published on arXiv detailing new findings in binary analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Bamberg County School District
• Binary Analysis Tasks
• binary code search
• Binary Code Similarity Detection
• Binary function embedding models
• call graph
• Call graphs for languages with parametric polymorphism
• Graph-Based Models of Cortical Axons for the Prediction of Neuronal Response to Extracellular Electrical Stimulation
• inter-procedural context
• Malware classification and detection using audio descriptors
• reverse engineering
• Vulnerability Detection and Resolution in Internet of Things (iot) Devices

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →