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


Public security advisories and PoCs for vulnerabilities discovered in open-source web software, with root-cause analysis, CVE references,…

Trace-assisted VMProtect devirtualization research platform: version front-ends feed a shared Remill/LLVM backend to lift handlers, recover dataflow,…

A lifecycle benchmark for black-box LLM extraction attacks, defenses, and adaptive attacks.

LLM safety: analyze how fine-tuning shifts refusal behavior and evaluate layer-freezing and low-rank defenses.

Reverse engineering notes and a working PoC for the macOS PackageKit symlink-following bug (CVE-2026-28912), with disassembly diff of the 26.6 fix.

Technical analysis and PoC for CVE-2026-24516: Unauthenticated Root Remote Code Execution in DigitalOcean Droplet Agent (CVSS 10.0).

Temporary Root Research on Poco M7 Plus (SM6375) via Qualcomm GBL Exploit (CVE-2026-24088) + GhostLock Kernel Analysis (CVE-2026-43499)

OWASP framework cataloging the top 10 security risks in neocloud and AI data center infrastructure, covering hardware, networking, isolation,…

Advisory and detection guidance for CVE-2026-73570, an unauthenticated OS command injection in Zimbra SNMP notification processing leading to remote…

Research code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…

Embeds and detects keyed, style-based watermarks in LLM-generated Python, Java, and C++ code via CST rewriting, preserving functional correctness and…

Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…

Curated index of deep learning latency, energy-latency & timing (availability) attacks and defenses — companion to the ACM Computing Surveys…

Open-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…

Human-in-the-loop UI that converts natural-language or C/C++ protocol descriptions into a reviewable Protocol IR, then generates Sapic+/Tamarin…

Stuff like malware analysis reports on things I captured from my honeypot

Technical analysis of CVE-2026-72018, a Linux kernel out-of-bounds write in DIBS/ISM loopback, covering root cause, affected versions, detection, and…