Skip to content
#

attack-graph

Here are 52 public repositories matching this topic...

A Flipper Zero that stops guessing and starts reasoning: ML-guided RFID/NFC fuzzing & access-control auditing that turns raw card reads into a prioritized, explainable security assessment. Defensive-use only.

  • Updated Oct 29, 2026
  • Python
aapp-mart

AAPP-MART is a cybersecurity engine for AI-powered autonomous attack path prediction and multi-agent red team simulation. These capabilities include adversary emulation, threat modeling, security validation, risk assessment, and MITRE ATT&CK alignment.

  • Updated Nov 9, 2026
  • Python

Hybrid LSTM-Markov attack chain forecasting for MITRE ATT&CK. Learns from 4,849 campaign chains + 8,437 real intrusion traces. Generates 26,051 risk-ranked multi-step attack futures via constrained beam search. 86% next-step accuracy, 0.76 Pearson correlation with NCISS severity. SECRYPT 2026 submission.

  • Updated Jun 23, 2026
  • Python
pentest-navgrid

WSTG tells you what to cover. This tells you what the tests inside each line actually are: the procedure, the oracle that separates a real result from the thing that imitates it, and where a success can lead. One offline, self-contained HTML file — no server, no install, no network.

  • Updated Sep 14, 2026
  • Python

Neuro-symbolic RL agent that learns to pentest networks it has never seen — GPT-4o compiles CVE preconditions into a Z3 action mask over a GraphSAGE PPO policy. Zero-shot attack-graph transfer, negatives disclosed.

  • Updated Aug 7, 2026
  • Python

Formal-model-first lab for agents: finite-state models with Z3 bounded checks, gated execution with an intent ledger and reconciliation, field-level prediction-vs-observation diffs, model revision with regression cases, and offline replay bundles. Local-first: Temporal · FastAPI · React. Domain plugins: MAL, CAGE 4.

  • Updated Oct 16, 2026
  • Python

Lightweight Autonomous Intrusion Detection and Response System — real-time packet capture, adaptive baseline learning, micro-honeypot deception layer, causal attack graphs, and explainable automated blocking for small-scale networks.

  • Updated Jun 26, 2026
  • Python

PRISM (Team FORTZ, Byteathon BYT04): correlates Windows Security, Sysmon and Zeek DNS logs into one explainable attack story: where it started, where the attacker is now, and a predicted next target. Rule-based correlation, MITRE ATT&CK mapping, 9 evidence-grounded investigation agents, real-time feed. FastAPI + React.

  • Updated Oct 10, 2026
  • Python

Add this topic to your repo

To associate your repository with the attack-graph topic, visit your repo's landing page and select "manage topics."

Learn more