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

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

A serverless networking protocol designed for resilient state synchronization between autonomous agents in fragmented, low-bandwidth networks

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

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

Voice-based detective interrogation game. Mistral Large 3 + Voxtral STT + ElevenLabs TTS. Built for the Mistral Worldwide Hackathon 2026.


Research code for red-teaming AI auto-mode monitors, including simulation evals, fuzzing, and monitor implementations for Claude Code and Codex…

This repository demonstrates a machine learning pipeline for detecting MITRE ATT&CK techniques from logs and enriching the output using a local LLM.

FLNET2023 is a dataset designed for intrusion detection in Federated Learning scenarios. It's built using the CORE emulator, simulating a realistic…

Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…

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

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

A next-generation multi-echelon anti-ransomware fortress for Windows, combining hypervisor, eBPF, AI deception, and hardware-enforced security.

This repository contains the official implementation of the paper "[Safety in Batches? Understanding and Mitigating Safety Failures in Batch…

Research code reproducing multi-turn LLM jailbreak experiments (FITD, MRCJ, ActorAttack, X-Teaming) from the SoK intent-oriented systematization…

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

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

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