Investigating attacks using Splunk Enterprise logs and creating SPL intrusion detection searches based on known attacker TTPs and anomaly behavior derived from statistical baselines

A curated list of awesome privilege escalation

IoT HackBot: A collection of Claude Skills and custom tooling for hybrid IoT pentesting

Use Hugging Face with JavaScript

my notes

Elastic Malware Benchmark for Empowering Researchers

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

An adaptive sampling framework for Reinforce-style LLM post training.

Awesome Mixture of Experts (MoE): A Curated List of Mixture of Experts (MoE) and Mixture of Multimodal Experts (MoME)

The Foundation AI Testing Hub (FAITH) is a benchmarking tool used to assess LLMs competency on (cybersecurity) knowledge/tasks.

BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.

This benchmark tests how well LLMs incorporate a set of 10 mandatory story elements (characters, objects, core concepts, attributes, motivations, etc.) in a short creative story

Lightning fast data version control system for structured and unstructured machine learning datasets. We aim to make versioning datasets as easy as versioning code.

My personal blog

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

On the Theoretical Limitations of Embedding-Based Retrieval

A benchmark for LLMs on complicated tasks in the terminal

Generating, validating and running exploitable verifiable coding problems

Fast, Flexible and Portable Structured Generation

The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"

Data about all known supply-chain attacks through history

A curated collection of privacy-preserving machine learning techniques, tools, and practical evaluations. Focuses on differential privacy, federated learning, secure computation, and synthetic data…

SynthTextEval: A Toolkit for Generating and Evaluating Synthetic Data For High-Stakes Domains (EMNLP 2025 System Demonstration)

A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on modern AI technologies like Large Language Models (LLMs), Agents, and Multi-Moda…