Tutorial

On this tutorial, we will learn the key components of AIJack.

• 1. Federated Learning
  • 1.1. FedAVG
  • 1.2. FedAVG with Paillier Encryption
  • 1.3. FedAVG with Sparse Gradient
  • 1.4. FedMD: Federated Learning with Model Distillation
  • 1.5. SecureBoost: Vertically Federated XGBoost with Paillier Encryption
• 2. Model Inversion
  • 2.1. MI-FACE
  • 2.2. Gradient-based Model Inversion Attack against Federated Learning
  • 2.3. GAN Attack
  • 2.4. Soteria: : Provable Defense against Privacy Leakage in Federated Learning g from Representation Perspective
  • 2.5. Mutual Information-based Defense
• 3. Label Leakage
  • 3.1. Split Learning and Label Leakage
• 4. Membership Inference
  • 4.1. Memership Inference
• 5. Poisoning Attack
  • 5.1. Poisoning Attack against Federated Learning
  • 5.2. Poisoning Attack against SVM
• 6. Backdoor Attack
  • 6.1. Backdoor Attack against Federated Learning
• 7. Evasion Attack
  • 7.1. Evasion Attack against SVM
  • 7.2. DIVA
  • 7.3. Exploring Adversarial Example Transferability and Robust Tree Models
  • 7.4. PixelDP
• 8. Differential Privacy
  • 8.1. Differential Privacy and Moment Accountant
  • 8.2. MI-FACE vs DPSGD
  • 8.3. AdaDPS
  • 8.4. DPlis
• 9. K-anonymity
  • 9.1. K-anonymity
• 10. Debugging
  • 10.1. Neuron Coverage
  • 10.2. Model Assertions
• 11. Homomorphic Encryption
  • 11.1. Paillier Encryption