Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacy© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
hackersignal — 7.45M-document cyber threat intelligence corpus and benchmark linking hacker-forum, exploit and advisory text to 340K NVD CVEs, with temporal splits for retrieval and exploit-type classification. | Kitploit
Tools/GitHubGitHub/benampel/hackersignal
Vulnerability AnalysisExploitationInformation GatheringThreat IntelligenceMachine LearningPapers & ResearchLearning & EducationCrawlerCurated Resources
GitHubbenampel/hackersignal

hackersignal

7.45M-document cyber threat intelligence corpus and benchmark linking hacker-forum, exploit and advisory text to 340K NVD CVEs, with temporal splits for retrieval and exploit-type classification.

3984722 days agoReviewed by Kitploit
View RepositoryWebsite

Most Popular

View all →

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    1.0k
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    590
  • 3

    looking-glass

    anonghosty/looking-glass

    CSIRT platform that ingests Shadowserver reports into MongoDB and replays them as interactive maps, analysis, findings, advisories and executive dashboards.

    383
  • 4

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    322
  • 5

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    309
  • 6

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    283

Explore all tools

Browse our collection of tools

View all tools →
Share

HackerSignal

A Multi-Source, CVE-Linked Corpus and Prospective Benchmark for Cyber Threat Intelligence

NeurIPS 2026 arXiv Hugging Face Dataset Croissant Datasheet Data license: CC BY 4.0 Code license: MIT
Documents Sources CVEs Tasks Python 3.10+ PyTorch GitHub stars Last commit

Paper (arXiv) · Dataset · Benchmark tasks · Quick start · Reproduce · Citation


HackerSignal is a cyber threat intelligence (CTI) dataset and benchmark that links what hackers discuss in underground and security communities to the vulnerabilities those discussions concern. It aggregates 7,447,646 exact-deduplicated documents from 64 public forum and source identifiers across eight source layers, from hacker forums and exploit archives to NVD CVE descriptions, security advisories, bug-bounty reports, fix commits and CISA Known Exploited Vulnerabilities. On top of the corpus it defines three benchmark tasks with temporal train/validation/test splits: CVE linkage retrieval, 8-class exploit type classification, and CVE-disjoint temporal generalization to vulnerabilities published after training.

HackerSignal is published in the NeurIPS 2026 Evaluations & Datasets Track. Preprint: arXiv:2605.03158.

At a glance

Documents7,447,646 (exact-deduplicated)
Sources64 public forum / source identifiers in 8 source layers
Hacker-community layer6,966,014 posts (largest forums: Gayanku, Antichat, Evolution, AntiOnline, HackForums)
Vulnerability reference340,536 NVD CVE descriptions (the retrieval corpus for Tasks 1 and 3)
Other layersExploit archives, exploit Q&A, advisories, bug-bounty disclosures, fix commits, CISA KEV
LanguagesEnglish plus substantial non-English content: Russian (antichat, 1.82M posts), Persian (persiantools, 280K), and others; 30.2% of CVE-linked forum posts are Cyrillic-heavy
Time span1988–2026
SplitsTemporal: test data postdate training data in every task
MetadataCroissant JSON-LD, Datasheet for Datasets, source release manifest
LicenseData CC BY 4.0 (LICENSE-DATA), code MIT (LICENSE); per-source terms in release governance

Benchmark tasks

TaskTypeTrainValTestCorpus / totalMetrics
1. CVE Linkage Retrieval (CVE-R)Retrieval56,6922,5841,990340,536R@1, R@5, R@10, MRR
2. Exploit Type Classification (ETC)8-class classification64,4134,7351,73570,883Macro-F1, per-class F1
3. Temporal Generalization (TG)CVE-disjoint retrieval56,8332,5351,898340,536R@1, R@5, R@10, MRR
  • Task 1 (CVE-R): given exploit, advisory, fix-commit or bug-bounty text, retrieve the CVE it refers to from all 340,536 NVD descriptions. Gold links come from source metadata.
  • Task 2 (ETC): classify exploit text into injection, XSS, memory corruption, denial of service, file inclusion, authentication and access control, remote code execution, or information disclosure. Train < 2020, validation 2020–2022, test ≥ 2023.
  • Task 3 (TG): the Task 1 retrieval problem with strictly disjoint gold CVE sets: training CVEs were published before 2022, validation CVEs in 2022–2023, and test CVEs in 2024 or later. The Task 3 test queries are a subset of the Task 1 test queries.

The baseline ladder covers BM25, four dense bi-encoders (all-MiniLM-L6-v2, all-mpnet-base-v2, BGE-base-en-v1.5, E5-base-v2) and a BM25 + dense hybrid for retrieval, and Decision Tree, TF-IDF + logistic regression, linear SVM, RNN, GRU, LSTM, BiLSTM, SecBERT, SecureBERT and CySecBERT for classification. Scores are in Baseline results below and in the paper (Tables 5–7).

Baseline results

Camera-ready numbers, rebuilt end to end from the released data on one Apple M5 Pro (PyTorch 2.14.1, MPS). Every value below is generated from results/camera_ready/results.csv; per-run seeds, model revisions and data hashes are in results/camera_ready/provenance.json. Retrieval uses zero-shot encoders over all 340,536 NVD descriptions, and MRR is MRR@10. The forum-post pilot masks every CVE string in the 1,964 CVE-linked hacker-community posts and retrieves the cited CVE from the same corpus.

ModelTask 1 R@1Task 1 MRRTask 3 R@1Task 3 MRRForum-post pilot MRR
BM250.5950.6360.6200.6600.064
all-MiniLM-L6-v20.6550.7090.6700.7220.073
all-mpnet-base-v20.6260.6820.6470.7030.065
BGE-base-en-v1.50.6530.7140.6670.7260.078
E5-base-v20.6490.7100.6630.7210.072
Hybrid BM25 + mpnet0.6790.7110.6980.730–

The top two models are statistically tied on both tasks (paired bootstrap, Task 1 ΔMRR 0.003, 95% CI [-0.013, 0.019]; Task 3 ΔMRR 0.004, 95% CI [-0.012, 0.020]).

Task 2 (exploit type classification, 1,735 test exploits). Transformers are fine-tuned on a 15K training subsample.

ModelMacro-F1 (mean ± SD, 3 seeds)95% CI
Decision Tree0.702 ± 0.007[0.677, 0.727]
TF-IDF + LR0.772 ± 0.000[0.744, 0.795]
SVM0.799 ± 0.000[0.773, 0.822]
RNN0.436 ± 0.031[0.415, 0.455]
GRU0.858 ± 0.001[0.840, 0.874]
LSTM0.824 ± 0.013[0.804, 0.841]
BiLSTM0.856 ± 0.003[0.837, 0.872]
SecBERT0.852 ± 0.007[0.833, 0.870]
SecureBERT0.892 ± 0.008[0.875, 0.907]
CySecBERT0.898 ± 0.003[0.882, 0.913]

CySecBERT and SecureBERT do not differ significantly (paired Δ 0.006, 95% CI [-0.003, 0.016]).

Quick start

The test splits are committed in data/benchmark_v2/. Training and validation splits and the full corpus are on the Hugging Face Hub as JSONL files:

from datasets import load_dataset
Download Tool