Class PrivacyMechanismBase<TModel, T>

Namespace

AiDotNet.FederatedLearning.Privacy

Assembly

AiDotNet.dll

Base class for privacy mechanisms in federated learning.

public abstract class PrivacyMechanismBase<TModel, T> : FederatedLearningComponentBase<T>, IPrivacyMechanism<TModel>

Type Parameters

TModel

Model/update representation.

T

Numeric type.

Inheritance

object

FederatedLearningComponentBase<T>

PrivacyMechanismBase<TModel, T>

Implements

IPrivacyMechanism<TModel>

Derived

GaussianDifferentialPrivacyVector<T>

GaussianDifferentialPrivacy<T>

Inherited Members

FederatedLearningComponentBase<T>.NumOps

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Methods

ApplyPrivacy(TModel, double, double)

Applies privacy-preserving techniques to a model update before sharing it.

public abstract TModel ApplyPrivacy(TModel model, double epsilon, double delta)

Parameters

model TModel

The model update to apply privacy to.

epsilon double

Privacy budget parameter - smaller values provide stronger privacy.

delta double

Probability of privacy guarantee failure - typically very small (e.g., 1e-5).

Returns

TModel

The model update with privacy mechanisms applied.

Remarks

This method transforms model updates to provide privacy guarantees while maintaining utility.

For Beginners: This is like redacting sensitive parts of a document before sharing it. You remove or obscure information that could identify individuals while keeping the useful content intact.

Common techniques:

• Differential Privacy: Adds random noise proportional to sensitivity
• Gradient Clipping: Limits the magnitude of updates to prevent outliers
• Local DP: Each client adds noise before sending updates
• Central DP: Server adds noise after aggregation

For example with differential privacy:

1. Client trains model and computes weight updates
2. Applies gradient clipping to limit maximum change
3. Adds calibrated Gaussian noise to each weight
4. Sends noisy update to server
5. Even if server is compromised, individual data remains private

GetMechanismName()

Gets the name of the privacy mechanism.

public abstract string GetMechanismName()

Returns

string

A string describing the privacy mechanism (e.g., "Gaussian Mechanism", "Laplace Mechanism").

Remarks

For Beginners: This identifies which privacy technique is being used, helpful for documentation and comparing different privacy approaches.

GetPrivacyBudgetConsumed()

Gets the current privacy budget consumed by this mechanism.

public abstract double GetPrivacyBudgetConsumed()

Returns

double

The amount of privacy budget consumed so far.

Remarks

Privacy budget is a finite resource in differential privacy. Each time you share information, you "spend" some privacy budget. Once exhausted, you can no longer provide strong privacy guarantees.

For Beginners: Think of privacy budget like a bank account for privacy. Each time you share data, you withdraw from this account. When the account is empty, you've used up your privacy guarantees and should stop sharing.

For example:

• Start with privacy budget ε=10
• Round 1: Share update with ε=1, remaining budget = 9
• Round 2: Share update with ε=1, remaining budget = 8
• After 10 rounds, budget is exhausted