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

Sandbox untrusted code with safe access to the host.
Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…

Firmware reverse engineering of the Philips PM5139 / PM5138A / PM5136 function generators: 8051 emulators used as measuring instruments, 35 sections…

Technical whitepaper dissecting JioPC cloud VDI architecture, including hardware specs, session termination mechanisms, and security limitations,…

A machine learning toolkit for log parsing [ICSE'19, DSN'16]

Automated framework for frontier AI safety evaluation that synthesizes executable, pressure-rich test environments to uncover latent risks in…

Collection of Zero Day Initiative conference presentations, whitepapers, and vulnerability research publications covering exploit techniques and…

Container escape proof-of-concept exploits for CVE-2026-80521 and CVE-2026-52910, with a disposable QEMU/Ubuntu VM harness for safe PoC execution.

Cryptanalysis golf: break schemes and prove it in Lean 4. Proof-of-concept board.

A comprehensive browser extension (.xpi) malware scanner which checks for many common malware tricks like:, credential-stealers obfuscation tactics,…

Evidence and data for the Sorami technical report on security defaults of 15 AI serving, vector database and MCP Helm charts on Kubernetes.

Tozed ZLT X300 5G CPE — Remote Root Code Execution via SDR Rogue Base Station (CVE-2026-2035703, CWE-78, CVSS 9.8) — Coordinated Disclosure

Quickly find differences and similarities in disassembled code

An Open-Source Package for Textual Adversarial Attack.

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

Research pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…

Defensive framework that maintains a safety-focused shadow memory to detect and block prompt-injection and long-horizon threats against LLM agents…

Device-bound CVE-2026-64560 adaptation for RedMi K80pro miro OS 3.0.304.0