#1Security papers, research projects, technical references, and reproducible material for defensive or authorized analysis.
Kitploit recommended

An audit-oriented risk model for how agent-generated inferences can change epistemic status, gain operational authority, and influence later…

Writeup of an SSCTF pwn450 challenge covering Windows kernel exploitation of MS16-034, including vulnerability analysis and privilege escalation…

Cross-agent tracing and security-diagnosis system for tool-using LLM agents: normalizes trace events, builds provenance graphs, extracts…

Collection of proof-of-concept exploits and vulnerability research artifacts published by Trend Micro's Zero Day Initiative, covering SCADA, RPC, and…

Collects multi-source security logs from reproducible Docker attack scenarios, builds attack chains, and provides the SecLog-Bench-216 benchmark for…

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…

Code, aggregate data and LaTeX source for 'Who Patches the Lightning Network? Evidence from Release Lines in Gossip, 2023-2026' (arXiv:2610.30350)

Reverse engineering Vidar Stealer: From obfuscated memory strings to Chrome process injection, malicious JS execution, and active session hijacking…

:robot: (Vibecoded prototype) NO, There is an easy way to exploit this vulnerability!

Proof-of-concept code and research notes for QPACK/HTTP-3 vulnerabilities (CVE-2025-64702, CVE-2026-12523, CVE-2025-13945) for authorized lab testing.

Proof-of-concept code for CVE-2026-109618 and CVE-2026-109619 (php2shell bypass), packaged for authorized lab reproduction and vulnerability research.

Collection of YARA rules for hunting malware, malicious Office documents, and exploit artifacts, with references to samples and research write-ups.

Research on persistent prompt injections via memory features in Claude, Gemini, and ChatGPT, with reproduction steps, datasets, and proofs for…

Secret-Use Delegation Protocol — protocol-level secret use for agentic systems

Jailbreak vulnerability across early-exit depths LLMs. Published at NeurIPS 2026 in the FLMSec workshop

Reference implementation of privacy-preserving face recognition using replicated secret sharing in MP-SPDZ, with quantized GhostFaceNet inference,…

Reproducible Colab pipeline that grounds six AI Security Literacy competency dimensions in public benchmarks and survey microdata, producing figures,…

Security & Privacy in Computing(Fall 2018), Final Group Project at JHUISI, clamscan vulnerability in Cisco's ClamAV 0.99.3