
ghost
Detects process injection and memory manipulation used by malware. Finds RWX regions, shellcode patterns, API hooks, thread hijacking, and process…

Detects process injection and memory manipulation used by malware. Finds RWX regions, shellcode patterns, API hooks, thread hijacking, and process…

The repository that contains the algorithms for generating domain names, dictionaries of malicious domain names. Developed to research the…

A network packet forensics tool for SSH

Research implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.

SAFE: Self-Attentive Function Embeddings for binary similarity

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

LLM-agent-powered concolic execution engine that instruments source code, summarizes path constraints in natural language, and generates test cases…

I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in…

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

AI 驱动的 SOC 仿真平台

SAFE embeddings to match functions in yara

Malware detection using learning and information retrieval for Android

reverse engineering SynthID for text

A structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…

Evolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…

Local-first geolocation engine that identifies precise GPS coordinates of street-level photos using CosPlace, ALIKED, and LightGlue computer vision…

DNS Proxy that is simple and fast with not so simple features. Focused on routed DNS forwarding, filtering and parental control.