
Log4Shell-vulnerability-CVE-2021-44228-
This repository provides an in-depth analysis of the Log4Shell vulnerability (CVE-2021-44228) and implements a machine learning-based approach to…

This repository provides an in-depth analysis of the Log4Shell vulnerability (CVE-2021-44228) and implements a machine learning-based approach to…

An open-source digital image forensic toolset

Interactive dashboards and libraries for responsible AI model debugging, covering error analysis, fairness, interpretability, counterfactuals, causal…

A Deep Learning Approach for Password Guessing (https://arxiv.org/abs/1709.00440)

LSTM-based classifier for detecting domain generation algorithm (DGA) domains, with Keras implementations of neural network and bigram models for DNS…

AI 驱动的 SOC 仿真平台

reverse engineering SynthID for text


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

Detection of rootkit file hiding activities through analysis of shifts in kernel function execution times.

Advanced detection of port scanning, DoS and malware attacks using Machine Learning techniques

Code for 'Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control'

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

Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…

Proof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…

Research codebase for privacy evaluation of quantized neural networks: trains target/shadow models under PTQ/QAT and runs membership-inference…

Research code for Rubric-Induced Preference Drift (RIPD): evolutionary rubric search, benchmark-preserving selection, and DPO policy misalignment…

Research pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…