Ghidra

Reverse Engineering Tutorial Explores Hybrid Analysis of Linux x86-64 Crackme Using Ghidra and GDB

A detailed three-part tutorial series examines the crackme binary Getting started keygen by Mazzotti on Linux x86-64. The first installment covers initial file inspection with file and strings utilities, identification of the ELF format and PIE properties, and loading the stripped binary into Ghidra to locate the entry point and main function. Analysts reconstruct stack frames, resolve optimized prologues, and correct Ghidra's variable sizing errors through dynamic confirmation in GDB. The series emphasizes hybrid static-dynamic methodology: decompiler hypotheses are tested with breakpoints and memory examination, then fed back to refine types and structures. Future parts will cover mutation testing, hidden C++ structures, and full Python reconstruction of the validation algorithm without patching branches.

Automating Malware Reverse Engineering with Local LLMs, PyGhidra and Neo4j Graphs

A researcher has developed an automated pipeline that uses local large language models to analyze decompiled malware code extracted via PyGhidra. The system loads functions, call graphs, strings and imports into a Neo4j graph database to preserve context across hundreds of functions. Each function is sent to a local Qwen3 model running in LM Studio together with its neighboring call-graph context, producing structured JSON output on purpose, IOCs, tags and evasion techniques. Aggregated capabilities and behavioral patterns such as file encryption and C2 communication are then derived through graph queries. Testing on a WannaCry sample from MalwareBazaar processed 195 functions in 126 minutes and correctly identified File Encryption, C2 Communication and Anti-Analysis behaviors with 100 percent confidence. The approach keeps all sensitive indicators inside a local environment and avoids context overflow and censorship issues common with cloud-based models.