pasquini-dario

watchtower. Watchtower — monitor, inspect, and debug all API traffic between AI coding agents (Claude Code, Codex CLI) and their APIs, with a real-time web dashboard.

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

magika. Fast and accurate AI powered file content types detection

Hashcat-MCP. MCP wrapper for Hashcat – automate hash cracking with natural language

better_opts_attacks. Jupyter Notebook

apple_generative_model_safety_decrypted. Decrypted Generative Model safety files for Apple Intelligence containing filters

neural-engine. Everything we actually know about the Apple Neural Engine (ANE)

apple-on-device-openai. OpenAI-compatible API server for Apple on-device models

vulhub. Pre-Built Vulnerable Environments Based on Docker-Compose

AIOpsLab. A holistic framework to enable the design, development, and evaluation of autonomous AIOps agents.

awesome-LLM-AIOps. A list of awesome academic researches and industrial materials about Large Language Model (LLM) and Artificial Intelligence for IT Operations (AIOps).

holmesgpt. SRE Agent - CNCF Sandbox Project

mt19937-reversible. Rewind that Mersenne Twister PRNG and recover the seed

llm-honeypot. HTML

TopicLLM_Granularity_Hallucination. Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling

genai-pentest-paper. This repo contains the codes for the experiments of the paper "AutoPenBench: Benchmarking Generative Agents for Penetration Testing".

auto-pen-bench. This repo contains the codes of the penetration test benchmark for Generative Agents presented in the paper "AutoPenBench: Benchmarking Generative Agents for Penetration Testing". It contains also the instructions to install, develop and test new vulnerable containers to include in the benchmark.

hackingBuddyGPT. Helping Ethical Hackers use LLMs in 50 Lines of Code or less..

PentestGPT. Automated Penetration Testing Agentic Framework Powered by Large Language Models

crewAI. Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

AI-model-card-analysis-HuggingFace. Jupyter Notebook

TheBigPromptLibrary. A collection of prompts, system prompts and LLM instructions

Awesome-ML-SP-Papers. A curated list of Meachine learning Security & Privacy papers published in security top-4 conferences (IEEE S&P, ACM CCS, USENIX Security and NDSS).

adams. Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries

preprocess. C/C++ preprocessor-like tool for a range of languages (i.e., #ifdef, #ifndef, #if-else, #include, etc. for Python, LaTeX, Bash, JavaScript, "whatever").

chat-ui. The open source codebase powering HuggingChat

tosdr-terms-of-service-corpus. This repository contains python code to create a corpus of 12,215 terms of service documents scraped from TOSDR, intended for legal, privacy, and natural language processing research.

avatar-paper. Jupyter Notebook

semantic-guesser. Training and testing of linguistic passwords models.

OMEN. OMEN: Ordered Markov ENumerator - Password Guesser

MIGP_python. MIGP (Might I Get Pwned) is a next generation password breach altering service to stop credential tweaking attack. This repository contains the code we used for the security simulations and performance analysis, the results of which are recorded in the published paper on USENIX Security 2022. For details, please refer to our paper.

migp-go. Go

credtweak. Password attack and defense using deep neural networks

pcfg_cracker. Probabilistic Context Free Grammar (PCFG) password guess generator

EmotiEffLib. Efficient face emotion recognition in photos and videos

FedFomo. Python

rethinking-honeywords. A Security Analysis of Honeywords

SplitNN_FSHA_torch. pytorch Version of SplitNN_FSHA

AppleNeuralHash2ONNX. Convert Apple NeuralHash model for CSAM Detection to ONNX.

nsparse. Sparse matrix computation library for GPU

GANTheftAuto. Python

gradient_disaggregation. Python

cppflow. Run TensorFlow models in C++ without installation and without Bazel

analytic-password-cracking. Python

rulesfinder. Machine-learn password mangling rules

MUSE. A library for Multilingual Unsupervised or Supervised word Embeddings

SplitNN_FSHA. Privacy attacks on Split Learning

integer_discrete_flows. Code release for Hoogeboom, Emiel, Jorn WT Peters, Rianne van den Berg, and Max Welling. "Integer Discrete Flows and Lossless Compression." Conference on Neural Information Processing Systems (2019).

nocrack. A new kind of password vault that fools the brute-force attacker by charning out decoy passwords.

subword-nmt. Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

peloton_bloomfilters. High performance bloomfilter

python-wordsegment. English word segmentation, written in pure-Python, and based on a trillion-word corpus.

face_toolbox_keras. A collection of deep learning frameworks ported to Keras for face analysis.

shap. A game theoretic approach to explain the output of any machine learning model.

FaceShifter. Try to reproduce FaceShifter

NEMO. Modeling Password Guessability Using Markov Models

python-bloomfilter. Scalable Bloom Filter implemented in Python

STGAN. STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

guess-calculator-framework. A framework for password-strength evaluation

PlotNeuralNet. Latex code for making neural networks diagrams

zxcvbn. Low-Budget Password Strength Estimation

Focal-Loss-implement-on-Tensorflow. The implementation of focal loss proposed on "Focal Loss for Dense Object Detection" by KM He and support for multi-label dataset.

class-balanced-loss. Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

PLR. Guessing passwords via Representation Learning, with style and a mixture of gaussians

tsne-cuda. GPU Accelerated t-SNE for CUDA with Python bindings

fastfilter_cpp. Fast Approximate Membership Filters (C++)

compare_gan. Compare GAN code.

gin-config. Gin provides a lightweight configuration framework for Python

OutDomainExamples. Adversarial Out-domain Examples for Generative Models: Adversarial examples for GAN generators