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

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

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

Robust audio watermarking framework embedding binary messages into magnitude spectrograms, with differentiable attack simulation, Q-Former pooling,…

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

Implementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"

Inference scaling for LLM safety assurance

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models (NeurIPS'26)

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

Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.

Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…

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

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

CybORG CAGE 2 environment updated for the paper "Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping"

Re-evaluating prompt-injection detectors on LLM agent tool outputs (paper draft, scripts, scores)

Analyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.

Defense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at…

Research code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…

A lifecycle benchmark for black-box LLM extraction attacks, defenses, and adaptive attacks.