🛡️ AI Security Toolkit
A red-team framework for testing the vulnerabilities of AI models through adversarial attacks, privacy leakage, and model exploitation techniques — built and maintained by @rishit03.
🚀 Features
✅ 5+ attack modules
✅ Unified logging and visualization
✅ Command-line interface (interactive menu)
✅ Modular, reusable, and pip-installable
✅ Built using TensorFlow, CleverHans, and Python's best practices
📦 Modules Included
| Module Name | Description |
|---|---|
| 🔓 Adversarial Attack (FGSM) | Confuses the model with small pixel changes |
| 💉 Label Flip Poisoning | Modifies training labels to reduce model accuracy |
| 🧠 Membership Inference Attack | Infers if a data point was used in training |
| 🪞 Model Inversion | Reconstructs training images from the model |
| 🧬 Model Stealing | Clones the target model using black-box queries |
| 🎯 Backdoor Trigger Attack | Embeds a hidden trigger that forces misclassification |
💻 CLI Usage
# After pip install or cloning locally
python ai_toolkit/run.py
1 maintainer
Metadata
1 maintainer
Release files for ai-security-toolkit 1.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ai_security_toolkit-1.1.2.tar.gz | 10.2 kB | Without provenance | Details for ai_security_toolkit-1.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ai_security_toolkit-1.1.2-py3-none-any.whl | Python 3 | none | any | Details for ai_security_toolkit-1.1.2-py3-none-any.whl |
Total release size: 24.7 kB
Release files / ai_security_toolkit-1.1.2.tar.gz
| Download URL | ai_security_toolkit-1.1.2.tar.gz |
|---|---|
| Size | 10.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e836edc9ee1c913057b591ec171045ea8170b1e09299344c95aef1c4768e392f
|
|
BLAKE2b-256 checksum How to use checksums |
411133cb6239001f4045c411029e7944ea0b9afefc0a1586bbde963e668ba0a7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.4
|
Release files / ai_security_toolkit-1.1.2-py3-none-any.whl
| Download URL | ai_security_toolkit-1.1.2-py3-none-any.whl |
|---|---|
| Size | 14.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
43faa0df6ea35022e8fd8b86529be1881de3040a0491e418bf86466013b70b65
|
|
BLAKE2b-256 checksum How to use checksums |
805a10fd40a8e522f1bdce449ef3771f1a137cf12de8cbc9d9f1e73f15cae13d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.4
|
Security for ai-security-toolkit 1.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
