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

AI Security Newsletter - A monthly digest of AI security research, insights, reports, upcoming events, and tools & resources

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

Demonstrates using machine learning to predict random number generator sequences, highlighting cryptographic weaknesses through adversarial analysis.

Agentic Framework for Synthesizing CodeQL Queries

OWASP Ontology-driven Threat Modelling framework

:hocho: CRIME attack PoC : a compression oracle attacks CVE-2012-4929 :hocho:

Extracted system prompt from Meta's AI Support Assistant on June 1, 2026

Information for CVE-2024-3094

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

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

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

CVE-2026-25262 applicability to Snapdragon 8 Gen 1 — experimental results

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

Reverse-engineered docs and tools for 8BitDo firmware encryption methods

Authenticated 0-click RCE against Linux 6.1.45 for CVE-2023-52440 and CVE-2023-4130

arm64/aarch64 port of V4bel/dirtyfrag (CVE-2026-43284). ESP-only - rxrpc path kernel-oopses on arm64 due to flush_dcache_page

Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…

Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models