Update Readme ad Format

README.md

@@ -234,6 +234,8 @@ Below you can find a list of papers and books that either use or extend AIJack.
 - Kapoor, Amita, and Sharmistha Chatterjee. Platform and Model Design for Responsible AI: Design and build resilient, private, fair, and transparent machine learning models. Packt Publishing Ltd, 2023.
 - Mi, Yuxi, et al. "Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddings." arXiv preprint arXiv:2308.02362 (2023).
 - Mohammadi, Mohammadreza, et al. "Privacy-preserving Federated Learning System for Fatigue Detection." 2023 IEEE International Conference on Cyber Security and Resilience (CSR). IEEE, 2023.
+- Huang, Shiyuan. A General Framework for Model Adaptation to Meet Practical Constraints in Computer Vision. Diss. Columbia University, 2024.
+- Liu, Can, Jin Wang, and Dongyang Yu. "RAF-GI: Towards Robust, Accurate and Fast-Convergent Gradient Inversion Attack in Federated Learning." arXiv preprint arXiv:2403.08383 (2024).
 
 # Contact
 

src/aijack/attack/__init__.py

@@ -1,5 +1,6 @@
 """Submodule for attack algorithms against machine learning.
 """
+
 from .base_attack import BaseAttacker  # noqa: F401
 from .evasion import (  # noqa: F401
     DIVAWhiteBoxAttacker,

src/aijack/attack/evasion/__init__.py

@@ -1,6 +1,7 @@
 """Subpackage for evasion attack, which creates a malicious data that the target
 machine learning model cannot correctly classify.
 """
+
 from .diva import DIVAWhiteBoxAttacker  # noqa: F401
 from .evasion_attack import Evasion_attack_sklearn  # noqa: F401
 from .fgsm import FGSMAttacker  # noqa: F401

src/aijack/attack/inversion/__init__.py

@@ -1,6 +1,7 @@
 """Subpackage for model inversion attack, which reconstructs the private data from
 the trained machine learning models.
 """
+
 from .gan_attack import GANAttackClientManager, attach_ganattack_to_client  # noqa: F401
 from .generator_attack import Generator_Attack  # noqa: F401
 from .gradientinversion import GradientInversion_Attack  # noqa: F401

src/aijack/attack/labelleakage/__init__.py

@@ -1,5 +1,6 @@
 """Subpackage for label leakage attack, which infere the private label information of the training dataset.
 """
+
 from .normattack import (  # noqa: F401
     NormAttackSplitNNManager,
     attach_normattack_to_splitnn,

src/aijack/attack/membership/__init__.py

@@ -1,6 +1,7 @@
 """Subpackage for membership inference attack, which reveals the confidential information
     about whether the target data is in the training dataset or not.
 """
+
 from .membership_inference import ShadowMembershipInferenceAttack  # noqa: F401
 
 __all__ = ["ShadowMembershipInferenceAttack"]

src/aijack/attack/poison/__init__.py

@@ -1,6 +1,7 @@
 """Subpackage for poisoning attack, which inserts malicious data to the training dataset,
 so that the performance of the trained machine learning model will degregate.
 """
+
 from .history import HistoryAttackClientWrapper  # noqa: F401
 from .label_flip import LabelFlipAttackClientManager  # noqa: F401
 from .mapf import MAPFClientWrapper  # noqa: F401

src/aijack/collaborative/__init__.py

@@ -1,6 +1,7 @@
 """Subpackage for collaborative learning, where multiple clients trains a single
 global model without sharing their local datasets.
 """
+
 from .core import BaseClient, BaseServer  # noqa: F401
 from .dsfl import DSFLAPI, DSFLClient, DSFLServer  # noqa : F401
 from .fedavg import (  # noqa: F401

src/aijack/collaborative/core/__init__.py

@@ -1,5 +1,6 @@
 """Subpackge implementing abstract classes for collaborative learning.
 """
+
 from .api import BaseFedAPI, BaseFLKnowledgeDistillationAPI  # noqa : F401
 from .client import BaseClient  # noqa: F401
 from .server import BaseServer  # noqa: F401

src/aijack/collaborative/dsfl/__init__.py

@@ -1,6 +1,7 @@
 """Implementation of DS-FL,  `Itahara, Sohei, et al. "Distillation-based semi-supervised federated learning for
 communication-efficient collaborative training with non-iid private data.
 " arXiv preprint arXiv:2008.06180 (2020).`"""
+
 from .api import DSFLAPI  # noqa : F401
 from .client import DSFLClient  # noqa : F401
 from .server import DSFLServer  # noqa : F401

src/aijack/collaborative/fedgems/__init__.py

@@ -1,5 +1,6 @@
 """Implementation of `Cheng, Sijie, et al. "FedGEMS: Federated Learning of Larger
 Server Models via Selective Knowledge Fusion." arXiv preprint arXiv:2110.11027 (2021).`"""
+
 from .api import FedGEMSAPI  # noqa: F401
 from .client import FedGEMSClient  # noqa : F401
 from .server import FedGEMSServer  # noqa: F401

src/aijack/collaborative/optimizer/__init__.py

@@ -1,5 +1,6 @@
 """Implementation of basic collaborative optimizers for neural network
 """
+
 from .adam import AdamFLOptimizer  # noqa: F401
 from .sgd import SGDFLOptimizer  # noqa: F401
 

src/aijack/defense/__init__.py

@@ -1,5 +1,6 @@
 """Subpackage for defense algorithms for machine learning models.
 """
+
 from .dp import DPSGDManager, GeneralMomentAccountant  # noqa: F401
 from .mid import VIB, KL_between_normals, mib_loss  # noqa:F401
 from .paillier import PaillierGradientClientManager, PaillierKeyGenerator  # noqa: F401

test/attack/inversion/test_ganattack.py

@@ -35,7 +35,7 @@ def __init__(self, nz, nc, ngf):
                 nn.ReLU(True),
                 # state size. (ngf*2) x 16 x 16
                 nn.ConvTranspose2d(ngf * 1, 1, 4, 2, 1, bias=False),
-                nn.Tanh()
+                nn.Tanh(),
                 # state size. (nc) x 64 x 64
             )