
LSTM-MI
A LSTM based framework for handling multiclass imbalance in DGA botnet detection

A LSTM based framework for handling multiclass imbalance in DGA botnet detection

Proof-of-concept testing environment for CVE-2021-30858, based on Google Project Zero's root cause analysis of an in-the-wild iOS exploit.

a scenario based on CVE-2022-25845 yielding a TP for metadata based SCA but a FN if the callgraph is used

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

An Open-Source Pre and Post Callback-Based Framework for macOS Kernel Monitoring.

Open framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…

Buffer Overflow Attack and Prevention for an FPGA Based Soft-Processor System - 7th International Conference on Innovation in Electronics and…

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

Proof of concept for CVE-2022-34913

Techniques and tools for Windows kernel exploitation, covering pool overflow exploitation, segment heap metadata abuse, and debugging scripts for…

A deep learning toolkit for log-based anomaly detection

Proof-of-concept implementation for CVE-2026-94128, provided for study and research purposes.

Proof-of-concept implementation for CVE-2026-94129, provided for study and research purposes.

WordPress PPOM for WooCommerce Plugin <= 33.0.15 is vulnerable to SQL Injection


Documents CP PLUS EZ-P21 IP camera CVEs: arbitrary code execution via debug feature and improper authentication of HTTP endpoints, with responsible…

Heap-based Buffer Overflow vulnerability in Apache HTTP Server with mod_xml2enc, xml2StartParse, and untrusted content

Rule-based CLI tool that grades organizational defenses against MITRE ATT&CK and D3FEND frameworks, detects security gaps, and proposes mitigations.…