AIBT: Adversarial Information Bottleneck Training
Privacy-preserving federated learning with information-theoretic privacy guarantees
Overview
AIBT (Adversarial Information Bottleneck Training) is a privacy-preserving federated learning framework that combines information bottleneck theory with adversarial training to achieve strong privacy guarantees while maintaining high model utility.
Key Features
- 🔒 Privacy-Preserving: Combines Information Bottleneck (IB) with adversarial training
- 🌐 Federated Learning: Distributed training with FedAvg aggregation
- 🛡️ Attack Resistant: Defends against Membership and Attribute Inference attacks
- 🚀 Easy to Use: Simple API for training and evaluation
- 📊 Built-in Metrics: Privacy attack evaluation included
Installation
pip install aibt-fl
From Source
git clone https://github.com/aibt/aibt.git
cd aibt/aibt_package
pip install -e .
Quick Start
import torch
from aibt import AIBTFL, AIBTModel, create_aibt_model, evaluate_privacy
# Create an AIBT model for your data
model = create_aibt_model(
input_dim=13, # Number of input features
num_classes=2, # Number of output classes
latent_dim=64, # Latent space dimension
num_sensitive_classes=2 # Number of sensitive attribute classes
)
# Initialize AIBT Federated Learning
aibt = AIBTFL(
model=model,
num_clients=10,
device="cpu",
learning_rate=0.001,
lambda_kl=0.01, # KL divergence weight (Information Bottleneck)
lambda_adv=1.0, # Adversarial loss weight
)
# Setup clients with their data
aibt.setup_clients(
client_datasets=client_data, # List of (X, y) tuples per client
sensitive_data=client_sensitive # Optional: sensitive attributes
)
# Train with federated learning
history = aibt.train(
num_rounds=100,
local_epochs=5,
test_data=(X_test, y_test),
verbose=True
)
# Evaluate privacy
privacy_metrics = evaluate_privacy(
model=model,
train_data=(X_train, y_train),
test_data=(X_test, y_test),
device="cpu"
)
print(f"Membership Inference AUC: {privacy_metrics['membership_auc']:.4f}")
print(f"Privacy preserved: {privacy_metrics['membership_auc'] < 0.55}")
Architecture
AIBT combines three key components:
Input → Encoder → Compressed Representation → Predictor → Output
↓
Adversary (tries to infer sensitive info)
↓
Gradient Reversal Layer
Loss Function:
L = L_task + λ₁ L_KL - λ₂ L_adv
L_task: Task-specific loss (e.g., cross-entropy)L_KL: KL divergence for information bottleneck compressionL_adv: Adversarial loss for privacy (with gradient reversal)
API Reference
Core Classes
AIBTFL
Main federated learning class with AIBT training.
AIBTFL(
model, # AIBTModel instance
num_clients=10, # Number of federated clients
device="cpu", # Device (cpu/cuda)
learning_rate=0.001, # Learning rate
batch_size=32, # Batch size
lambda_kl=0.01, # KL divergence weight
lambda_adv=1.0, # Adversarial loss weight
lambda_grl=1.0, # Gradient reversal strength
)
AIBTModel
Complete AIBT model with encoder, predictor, and adversary.
AIBTModel(
encoder, # Encoder network
predictor, # Task predictor
adversary, # Adversary network
lambda_kl=0.01, # KL weight
lambda_adv=1.0, # Adversarial weight
lambda_grl=1.0, # GRL strength
)
Model Components
GradientReversalLayer: Reverses gradients during backprop for adversarial trainingVariationalEncoder: Information bottleneck encoder with reparameterizationMLPEncoder: MLP encoder for tabular dataPredictor: Task prediction headAdversary: Sensitive attribute classifier
Privacy Metrics
from aibt import evaluate_privacy, evaluate_membership_inference, evaluate_attribute_inference
# Complete privacy evaluation
metrics = evaluate_privacy(model, train_data, test_data, sensitive_train, sensitive_test)
# Individual attacks
mia_metrics = evaluate_membership_inference(model, train_data, test_data)
aia_metrics = evaluate_attribute_inference(model, X, sensitive_attrs)
Hyperparameters
| Parameter | Default | Description |
|---|---|---|
lambda_kl |
0.01 | KL divergence weight (compression) |
lambda_adv |
1.0 | Adversarial loss weight (privacy) |
lambda_grl |
1.0 | Gradient reversal strength |
latent_dim |
128 | Latent space dimension |
learning_rate |
0.001 | Optimizer learning rate |
batch_size |
32 | Training batch size |
Hyperparameter Tuning
- Higher
lambda_kl: More compression, potentially lower accuracy - Higher
lambda_adv: Stronger privacy, may affect utility - Recommended range:
lambda_kl ∈ [0.005, 0.02],lambda_adv ∈ [0.5, 2.0]
Citation
If you use AIBT in your research, please cite:
@article{aibt2025,
title={Adversarial Information Bottleneck Training for Privacy-Preserving Federated Learning},
journal={IEEE Transactions on Neural Networks and Learning Systems},
year={2025}
}
References
- Tishby et al., "The Information Bottleneck Method", Allerton 1999
- Ganin & Lempitsky, "Domain-Adversarial Training of Neural Networks", JMLR 2016
- McMahan et al., "Communication-Efficient Learning of Deep Networks from Decentralized Data", AISTATS 2017
License
MIT License - see LICENSE for details.
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
Metadata
Release files for aibt-fl 1.0.0
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 |
|---|---|---|---|---|
| aibt_fl-1.0.0.tar.gz | 21.4 kB | Without provenance | Details for aibt_fl-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| aibt_fl-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for aibt_fl-1.0.0-py3-none-any.whl |
Total release size: 41.3 kB
Release files / aibt_fl-1.0.0.tar.gz
| Download URL | aibt_fl-1.0.0.tar.gz |
|---|---|
| Size | 21.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7e4f37970f56c504d3b94ccdc6e1ce721c3d1dee3f806733feb44a50a24c5801
|
|
BLAKE2b-256 checksum How to use checksums |
05f48f052d148d9d7a1543fe96b25a14b4aaf2b2b8fedfb5309b15aa90d604de
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.3
|
Release files / aibt_fl-1.0.0-py3-none-any.whl
| Download URL | aibt_fl-1.0.0-py3-none-any.whl |
|---|---|
| Size | 19.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b7d65e4d87acf5d3702f40acac254d2d4bc3815453fcae4c0bb0f5f81a0b76b2
|
|
BLAKE2b-256 checksum How to use checksums |
e70559cadfff0615fad413ca6818d60666484a6011949698fd4bb4818671dfc5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.3
|
Security for aibt-fl 1.0.0
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.