
WebMirage
Adversarial image attacks on vision-language web agents, from visual grounding to browser execution

Adversarial image attacks on vision-language web agents, from visual grounding to browser execution

Open source binary analysis framework and decompiler built on LLVM and QEMU, lifting binaries to a readable intermediate representation for reverse…

MCP-enabled multi-agent framework for declarative YAML-driven agentic workflows, used for AI-assisted code auditing, vulnerability triage, and…

Policy-governed LLMSecOps framework providing AST-based SAST, secret scanning, supply-chain and multi-cloud CSPM checks, AI-BoM generation, and CI/CD…

Agentic Framework for Synthesizing CodeQL Queries

Minimal 587-byte static ELF exploit for CVE-2026-31431, achieving local privilege escalation via AF_ALG splice page cache corruption. No libc or…

Static Go proof-of-concept for CVE-2026-31431, leveraging Linux AF_ALG and splice(2) to trigger the vulnerability. Provides prebuilt binaries for…

Pure Rust proof-of-concept for CVE-2026-31431, targeting Linux x86_64 kernels with AF_ALG AEAD support. Static musl build, no runtime dependencies,…

Rust macros and Cargo subcommand to automate fuzzing with afl.rs, including corpus generation and harness implementation, integrated with Rust's…

An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.

Runtime instrumentation framework for building dynamic analysis tools: tracing, profiling, code coverage, memory debugging, fuzzing, and disassembly…

ROPfuscator is a fine-grained code obfuscation framework for C/C++ programs using ROP (return-oriented programming).

A Binary Genetic Traits Lexer Framework

Fuzzing Framework for Modules in Apache HTTPD Server

Ensemble framework for software vulnerability detection and repair using multiple large language models, with consensus analysis and evaluation tools…

Spring Framework RCE exploit (CVE-2022-22965) with analysis code and educational walkthrough for understanding the vulnerability and exploitation…

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

VulnAgent-X: A Layered Agentic Framework for Repository-Level Vulnerability Detection