jaimemorales52

jaimemorales52 / llm-ioc-detection

Public

Spring Boot backend for evaluating Large Language Models on the detection of Indicators of Compromise (IoCs) embedded as secrets in obfuscated JavaScript code. In this implementation, the IoC is an IP address hidden inside transformed JS files. The service exposes REST APIs to query multiple LLM providers and normalize their IoC detection responses

ioc java javascript llm sast
11
0
100% credibility
Found Mar 04, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Java
AI Summary

A research tool that embeds IP addresses as secrets into JavaScript code, applies obfuscation and encryption pipelines, queries multiple large language models to detect them, and compiles normalized results for analysis.

How It Works

1
🔍 Discover the secret hunter

You hear about a clever tool that tests if smart AI brains can spot hidden dangers like secret addresses tucked away in website code.

2
🔗 Link your AI helpers

You connect popular AI thinkers like ChatGPT, Gemini, and others by sharing simple access passes so they can peek at the code.

3
🚀 Wake up the analysis station

With one easy start, your personal testing lab comes alive on your computer, ready to scramble and check code.

4
📤 Feed in your code

You upload a simple website script file or point to a folder of them, and it automatically hides a test secret inside while scrambling it in fun ways like renaming, encoding, and more.

5
🤖 Let AIs play detective

The connected AIs take turns examining each scrambled version, deciding if they spot the hidden secret and what it is.

📊 See the detective report

You get a clear table of results showing which AIs succeeded, failed, or weren't sure, plus stats on their spotting skills across all scrambles.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is llm-ioc-detection?

This Spring Boot backend evaluates how Large Language Models detect Indicators of Compromise like IP addresses hidden as secrets in obfuscated JavaScript code. Upload a JS file or directory via REST APIs, and it embeds an address, applies obfuscation and encryption pipelines (base64, XOR, AES, dead code), queries providers like OpenAI, Anthropic, Gemini, Grok, and normalizes responses to YES/NO/DON'T_KNOW plus extracted values. Results export to Excel or CSV for easy analysis, perfect for github spring ai experiments in a spring boot maven setup.

Why is it gaining traction?

Multi-LLM support with normalized outputs stands out—no more manual parsing across APIs. Batch-process directories for scalable tests, skipping boilerplate prompts and handling rate limits. Spring Boot's REST endpoints and spring boot initializr compatibility make it quick to fork on github spring boot repos for custom spring security or oauth2 tweaks.

Who should use this?

Security researchers benchmarking LLMs against malware evasion tactics. Devs prototyping AI-driven scanners for github spring framework issues like leaked addresses in JS bundles. Academics replicating LLM papers on code secrets, using spring boot starter for rapid spring boot version upgrades.

Verdict

Solid for research prototypes—MIT-licensed, detailed README with API usage, but 11 stars and 1.0% credibility signal early maturity; expect tweaks for production. Grab it if testing spring boot releases like spring boot 4 previews, but pair with your own spring github examples for reliability. (198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.