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

CVE-2026-84411 root cause notes and a non-destructive probe (RouterOS before 7.24)

Honor WIN RT (AAK-AN00) CVE-2026-43499 temporary root - research notes

Demonstrate and analyze the CVE-2026-31802 path traversal vulnerability in npm tar, enabling arbitrary file overwrite via symlink extraction.

SpeechBrain < 1.1.1 checkpoint metadata RCE via unsafe PyYAML parsing of CKPT.yaml.

Ghidra patch-diff analysis of the IOKit IODMACommand race condition in macOS Tahoe 26.6, with a non-destructive user-space PoC reproducing the…

A comprehensive guide to adversarial testing and security evaluation of AI systems, helping organizations identify vulnerabilities before attackers…

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

Reproducible macOS automountd lab PoCs and source-guided analysis for CVE-2026-84568 (fstype path traversal to root code execution) and…

Full static & memory analysis of Overlord RAT: Go agent architecture, HTTP/2 + WebSocket C2, reflective DLL injection, browser keylogging, and IOCs.…

Static reverse-engineering analysis of movement input heuristics in Source 2 engine, identifying structural edge cases in input automation and jump…

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

Proof-of-concept and technical write-up for CVE-2026-37107, an authenticated SSRF in HTMLy v3.1.1's feed import that enables arbitrary file read via…

Lightweight evaluation harness for RAG poisoning defenses that builds four-condition clean/poisoned records and reports prevented targets, net…

C proof-of-concept for CVE-2026-84520 in AppleFDEKeyStore, using IOKit to trigger the flaw; requires root privileges to run.

Research code for training adapters that make LLM agent backdoors survive benign fine-tuning, with trigger-rate scoring, SWE-bench evaluation, and…

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

Technical write-up of CVE-2026-88776, a pre-auth integer underflow in NetScaler nsppe's Oracle TNS record parser causing an out-of-bounds write and…