
SBOM-VEX-Taint-Analysis
Automated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX…

Automated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX…

Research code reproducing multi-turn LLM jailbreak experiments (FITD, MRCJ, ActorAttack, X-Teaming) from the SoK intent-oriented systematization…

Generalized VMProtect devirtualizer supporting versions 1.x–3.x. Standalone CLI tool and Ghidra plugin for automated bytecode decoding, handler…

Multi-stage prompt injection technique that bypasses LLM safety alignment via identity reassignment, refusal suppression, and output coercion,…

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learning

Research toolkit for analyzing AI agent behavioral patterns through multi-disciplinary corpus analysis. Parses session logs, runs 23 analytical…

Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

"In-depth reverse engineering analysis of an advanced multi-phase loader targeting Shellhost.exe, amsi.dll, mstscax.dll, and clbcatq.dll using module…

Full analysis of a never documented before Remote Access Trojan linked to Pjoao1578 toolchain

Reference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…

Reproduction pack and PoC script for CVE-2026-87796, an unauthenticated arbitrary file upload RCE in Multi Uploader for Gravity Forms <= 1.1.9, with…

Multi-language PoC (Python · Go · JS · C) and technical documentation for CVE-2025-63353, a critical predictable-default-PSK vulnerability in…

Code Implementation of "Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models"