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
Learning-to-Detect — Detects unknown jailbreak attacks in large vision-language models using hidden state analysis and autoencoders, with training and evaluation pipelines for robust safety monitoring. | Kitploit
Tools/GitHubGitHub/shuangliangx/learning-to-detect
Defensive ToolsVulnerability AnalysisMachine LearningAI SecurityAnomaly Detection
GitHubshuangliangx/learning-to-detect

Learning-to-Detect

Detects unknown jailbreak attacks in large vision-language models using hidden state analysis and autoencoders, with training and evaluation pipelines for robust safety monitoring.

Share
View Repository
1942 months agoNot yet reviewed

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models

Official implementation of “Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models.”

This repository contains the data-processing, hidden-state extraction, classifier training, safety-pattern auto-encoder, and evaluation code used in the project.

This release provides the LLaVA-v1.6-Vicuna-7B implementation. Adapting the pipeline to Qwen2.5-VL or CogVLM requires model-specific input processing and separately trained detectors.

Contents

  • Models
  • Repository Structure
  • Detection Pipeline
  • Datasets

Models

The experiments use the following base models:

  • LLaVA-v1.6-Vicuna-7B, a large vision-language model based on Vicuna.
  • Llama Guard 3 8B, a safety guardrail model used to assess generated responses.

Download the model weights separately and place them under:

asset/weights/

Repository Structure

.
├── asset/
│   ├── advbench/                 # AdvBench images
│   ├── harmbench/                # HarmBench DirectRequest images
│   ├── GQA/                      # GQA images
│   ├── HiddenStates/             # Extracted hidden states
│   └── weights/                  # Model weights (not included)
├── Benchmarks/                   # Evaluation benchmark metadata
├── vicuna/
│   ├── instructions/
│   │   ├── advbench.json
│   │   ├── GQA.json
│   │   └── harmbench.json        # HarmBench DirectRequest metadata
│   ├── qa.py
│   ├── qa-baseline.py
│   └── train.py
├── autoencoder.py
├── llama3_guard.py
└── test.py

Detection Pipeline

Some scripts use paths relative to their own working directory. Run the commands from the directories shown below.

1. Query the vision-language model

Query the model on the unsafe source data (AdvBench) and safe source data (GQA):

cd vicuna
python qa.py --dataset advbench
python qa.py --dataset GQA
cd ..

The HarmBench DirectRequest data can be queried with the same interface:

cd vicuna
python qa.py --dataset harmbench
cd ..

2. Assess and split model responses

Assess the generated AdvBench responses with Llama Guard 3:

python llama3_guard.py --file vicuna/instructions/advbench.json

Create the AdvBench and GQA training/test splits:

cd vicuna/instructions
python process.py
cd ../..

3. Extract hidden states

Extract hidden states for the evaluation benchmarks currently configured in vicuna/qa-baseline.py:

cd vicuna
python qa-baseline.py
cd ..

4. Train and test the MSCAV classifiers

cd vicuna
python train.py --train
python train.py --test
cd ..

5. Train the Safety Pattern Auto-Encoder (SPAE)

python autoencoder.py

6. Evaluate detection performance

python test.py

Datasets

Training and appendix data

DatasetRoleMetadataImages
AdvBenchUnsafe source datavicuna/instructions/advbench.jsonasset/advbench/
GQASafe source datavicuna/instructions/GQA.jsonasset/GQA/
HarmBench (DirectRequest)Unsafe-source experiment reported in the appendixvicuna/instructions/harmbench.jsonasset/harmbench/

The included HarmBench DirectRequest subset contains 320 image–request pairs. Image paths in harmbench.json are repository-relative and follow the same layout convention as AdvBench.

Evaluation benchmarks

Download the evaluation images from ModelScope: detecpolo/Learning-to-Detect and copy the downloaded asset/ directory into the repository root. The matching benchmark JSON files are provided in this repository under Benchmarks/.

Please refer to Section 4.1 and the appendices of our paper for dataset sources, attack construction, and experimental settings.

Download Tool

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.

    732
  • 2

    ghostlock-app

    yukonga/ghostlock-app

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

    506
  • 3

    ARTEX

    baarai/artex

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

    405
  • 4

    redforge

    cybersecurity91/redforge

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

    342
  • 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.

    261
  • 6

    antifox

    antifox-ai/antifox

    AI multi-agent autonomous penetration testing platform that runs recon, attack-surface discovery, exploitation validation and evidence-backed report delivery.

    259

Explore all tools

Browse our collection of tools

View all tools →