
degas
DGA-generated domain detection using deep learning models

DGA-generated domain detection using deep learning models

Fix-Like Artifacts With Embedded Defects

Deterministic PyGhidra extraction, triage, and local LLM compiler-backend pipeline for C reimplementation.

Benchmarking prompt injection detections for web agents.

Research related to the Power Tracks discovered in market microstructure.

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

Android Antivirus which doesn't require root, adb, ca install and cloud with many features and ways to detect more zero-day malware

CVPR2023: Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

Fine-tuning framework that applies first-order optimal safety calibration and periodic recalibration to LLMs, preserving safety-compatible updates…

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks

Framework for implementing Network Intrusion Detection Systems (NIDS) aimed at identifying anomalies in network flows using Federated Learning models.

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

A Java Burp Plugin that performs text clustering on responses to identify outliers/groups based on the actual content of the server responses, say…

FARO - Document Sensitivity Detector

Trajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…

ML-Based behavioral endpoint detection system for Linux machines

Research pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.