Model Extraction Attacks contra Redes Neurais Black-Box (2020-2026)

2026-04-08T00:00:00+00:00

Model Extraction Attacks on Black-Box Neural Networks (2020-2026)</h3>
monorep fresh co, ataques de extracao contra modelos black-box, surveys e literatura agregada.</p>

B3: Backdoor Attacks against Black-box Machine Learning Models | ACM Transactions on Privacy and Security - https://dl.acm.org/doi/10.1145/3605212</li>
[PDF] CloudLeak: Large-Scale Deep Learning Models Stealing Through Adversarial Examples | Semantic Scholar - https://www.semanticscholar.org/paper/CloudLeak:-Large-Scale-Deep-Learning-Models-Through-Yu-Yang/4d548fd21aad60e3052455e22b7a57cc1f06e3c3</li>
Stealing Neural Networks With Model Extraction Attacks, Dr. Nicholas Carlini | Commonwealth Cyber Initiative (CCI) | Virginia Tech - https://cyberinitiative.org/events-programs/2020/stealing-neural-networks-with-model-extraction-attacks-dr-nich.html</li>
I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences | ACM Computing Surveys - https://dl.acm.org/doi/10.1145/3595292</li>
GitHub - kzhao5/Model-Extraction-Stealing-Attacks-Machine-Learning-Literature - https://github.com/kzhao5/Model-Extraction-Stealing-Attacks-Machine-Learning-Literature</li>
First Model-Stealing Attack Reveals Secrets of Black-Box Production Language Models | Synced - https://syncedreview.com/2024/03/27/first-model-stealing-attack-reveals-secrets-of-black-box-production-language-models/</li>
A realistic model extraction attack against graph neural networks - ScienceDirect - https://www.sciencedirect.com/science/article/abs/pii/S0950705124007780</li>
[1602.02697] Practical Black-Box Attacks against Machine Learning - https://arxiv.org/abs/1602.02697</li>
Practical Black-Box Attacks against Machine Learning | Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security - https://dl.acm.org/doi/10.1145/3052973.3053009</li>
Black-box targeted adversarial attacks for deep neural networks - ScienceDirect - https://www.sciencedirect.com/science/article/abs/pii/S0925231225016893</li> </ol>
Stealing Machine Learning Models via Prediction APIs (arxiv)</h3>
o paper seminal do Tramer e suas variantes, mais codigo de extracao via prediction API.</p>

[1609.02943] Stealing Machine Learning Models via Prediction APIs - https://arxiv.org/abs/1609.02943</li>
Stealing Machine Learning Models via Prediction APIs - https://www.usenix.org/system/files/conference/usenixsecurity16/sec16_paper_tramer.pdf</li>
Stealing machine learning models via prediction APIs | Proceedings of the 25th USENIX Conference on Security Symposium - https://dl.acm.org/doi/10.5555/3241094.3241142</li>
[1609.02943] Stealing Machine Learning Models via Prediction APIs (HTML version) - https://ar5iv.labs.arxiv.org/html/1609.02943</li>
[1609.02943v2] Stealing Machine Learning Models via Prediction APIs (Updated version) - https://arxiv.org/abs/1609.02943v2</li>
Efficient and Effective Model Extraction - https://arxiv.org/html/2409.14122v1</li>
Scholars@Duke publication: Stealing Machine Learning Models via Prediction APIs - https://scholars.duke.edu/publication/1493919</li>
GitHub - ftramer/Steal-ML: Model extraction attacks on Machine-Learning-as-a-Service platforms - https://github.com/ftramer/Steal-ML</li>
[PDF] Stealing Machine Learning Models via Prediction APIs | Semantic Scholar - https://www.semanticscholar.org/paper/Stealing-Machine-Learning-Models-via-Prediction-Tram%C3%A8r-Zhang/d15b21bdd117877c2d0e865b17d6a336737aea99</li>
Stealing Machine Learning Models via Prediction APIs | USENIX - https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/tramer</li> </ol>
model inversion attacks 2020-2025 (deep leakage from gradients)</h3>
inversao de modelo e vazamento por gradiente, com foco em federated learning e training de language models.</p>

Iterative and mixed-spaces image gradient inversion attack in federated learning | Cybersecurity - https://cybersecurity.springeropen.com/articles/10.1186/s42400-024-00227-7</li>
Understanding Deep Gradient Leakage via Inversion Influence Functions - PubMed - https://pubmed.ncbi.nlm.nih.gov/38606303/</li>
Deep leakage from gradients | Proceedings of the 33rd International Conference on Neural Information Processing Systems - https://dl.acm.org/doi/10.5555/3454287.3455610</li>
Wasserstein Distance-Based Deep Leakage from Gradients - PMC - https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10217429/</li>
Uncovering Gradient Inversion Risks in Practical Language Model Training | Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security - https://dl.acm.org/doi/10.1145/3658644.3690292</li>
Deep Leakage from Gradients | SpringerLink - https://link.springer.com/chapter/10.1007/978-3-030-63076-8_2</li>
Understanding Deep Gradient Leakage via Inversion Influence Functions - https://arxiv.org/html/2309.13016</li>
[1906.08935] Deep Leakage from Gradients - https://arxiv.org/abs/1906.08935</li>
Inverting Gradient Attacks Naturally Makes Data Poisons: An Availability Attack on Neural Networks - https://arxiv.org/html/2410.21453v1</li>
A Survey of the Implementations of Model Inversion Attacks | SpringerLink - https://link.springer.com/chapter/10.1007/978-3-031-30648-8_1</li> </ol>
ONNX, SafeTensors, serializacao de pesos</h3>
formatos de armazenamento de peso de rede neural e conversao entre eles. relevante pra entender superficie de ataque na serializacao.</p>

ONNX - https://huggingface.co/docs/transformers/en/serialization</li>
Safetensors, CKPT, ONNX, GGUF, and Other Key AI Model Formats | NEDNEX - https://nednex.com/en/what-are-safetensors/</li>
Model Weights File Formats in Machine Learning - https://learnopencv.com/model-weights-file-formats-in-machine-learning/</li>
Export to ONNX - https://huggingface.co/docs/transformers/v4.36.1/serialization</li>
justinchuby/onnx-safetensors | DeepWiki - https://deepwiki.com/justinchuby/onnx-safetensors</li>
Common AI Model Formats - https://huggingface.co/blog/ngxson/common-ai-model-formats</li>
python - How to convert safetensors model to onnx model? - Stack Overflow - https://stackoverflow.com/questions/77855742/how-to-convert-safetensors-model-to-onnx-model</li>
GitHub - justinchuby/onnx-safetensors: Use safetensors with ONNX - https://github.com/justinchuby/onnx-safetensors</li>
Save external data as safetensors - onnx/onnx - Discussion #5461 - https://github.com/onnx/onnx/discussions/5461</li>
GitHub - huggingface/safetensors: Simple, safe way to store and distribute tensors - https://github.com/huggingface/safetensors</li> </ol>
distributed training e sharding (FSDP)</h3>
tecnicas de sharding de modelo em treino distribuido, FSDP no centro.</p>

Fully Sharded Data Parallel: faster AI training with fewer GPUs Engineering at Meta - https://engineering.fb.com/2021/07/15/open-source/fsdp/</li>

Sharding, Model Parallelism on the IPU with TensorFlow: Sharding and Pipelining - https://docs.graphcore.ai/projects/tf-model-parallelism/en/latest/sharding.html</li> </ol> </li>
Sharded Data Parallelism - Amazon SageMaker AI - https://docs.aws.amazon.com/sagemaker/latest/dg/model-parallel-extended-features-pytorch-sharded-data-parallelism.html</li>
[2305.01868] Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models - https://arxiv.org/abs/2305.01868</li>
Introducing PyTorch Fully Sharded Data Parallel (FSDP) API, PyTorch - https://pytorch.org/blog/introducing-pytorch-fully-sharded-data-parallel-api/</li>
An Introduction to FSDP (Fully Sharded Data Parallel) for Distributed Training. | by Siddhartha Shrestha | Medium - https://medium.com/@siddharthashrestha/an-introduction-to-fsdp-fully-sharded-data-parallel-for-distributed-training-5e67adfa1712</li>
Decentralized and Distributed Machine Learning Model - https://www.scs.stanford.edu/17au-cs244b/labs/projects/addair.pdf</li>
[2407.19775] Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference - https://arxiv.org/abs/2407.19775</li>
Fully Sharded Data Parallelism (FSDP) - Edge AI and Vision Alliance - https://www.edge-ai-vision.com/2024/05/fully-sharded-data-parallelism-fsdp/</li>
Getting Started with Fully Sharded Data Parallel (FSDP2), PyTorch Tutorials 2.8.0+cu128 documentation - https://docs.pytorch.org/tutorials/intermediate/FSDP_tutorial.html</li> </ol>
model serving, checkpoints e weight storage</h3>
vulnerabilidades de serving, formatos de checkpoint e armazenamento de peso em escala. inclui o RAND sobre seguranca de pesos de modelos de fronteira.</p>

Save and load models | TensorFlow Core - https://www.tensorflow.org/tutorials/keras/save_and_load</li>
Architecting scalable checkpoint storage for large-scale ML training on AWS | Amazon Web Services - https://aws.amazon.com/blogs/storage/architecting-scalable-checkpoint-storage-for-large-scale-ml-training-on-aws/</li>
Model Weights File Formats in Machine Learning - https://learnopencv.com/model-weights-file-formats-in-machine-learning/</li>
What is Machine Learning Checkpointing? Deep Learning Models - https://www.deepchecks.com/glossary/machine-learning-checkpointing/</li>
Training checkpoints | TensorFlow Core - https://www.tensorflow.org/guide/checkpoint</li>
What is Machine Learning Checkpointing | Giskard - https://www.giskard.ai/glossary/machine-learning-checkpointing</li>
deep learning - what happens to model weights and how does checkpointing work? - Stack Overflow - https://stackoverflow.com/questions/75368038/what-happens-to-model-weights-and-how-does-checkpointing-work</li>
Securing AI Model Weights: Preventing Theft and Misuse of Frontier Models | RAND - https://www.rand.org/pubs/research_reports/RRA2849-1.html</li>
Saving and Loading Checkpoints, Ray 2.49.0 - https://docs.ray.io/en/latest/train/user-guides/checkpoints.html</li>
Tips and tricks for performing large model checkpointing - https://nebius.com/blog/posts/model-pre-training/large-ml-model-checkpointing-tips</li> </ol>
KnockoffNets / ActiveThief (codigo de extracao)</h3>
extracao de modelo via active learning sobre dados publicos nao anotados.</p>

ActiveThief: Model Extraction Using Active Learning and Unannotated Public Data | Request PDF - https://www.researchgate.net/publication/341891796_ActiveThief_Model_Extraction_Using_Active_Learning_and_Unannotated_Public_Data</li> </ol>
serving infrastructure security e upload de modelos</h3>
seguranca de infra de serving de redes neurais, vulnerabilidades e upload de modelos.</p>

How Effective Are Neural Networks for Fixing Security Vulnerabilities | Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis - https://dl.acm.org/doi/10.1145/3597926.3598135</li>
[2305.18607] How Effective Are Neural Networks for Fixing Security Vulnerabilities - https://arxiv.org/abs/2305.18607</li>
One Step Ahead in Cyber Hide-and-Seek: Automating Malicious Infrastructure Discovery With Graph Neural Networks - https://unit42.paloaltonetworks.com/graph-neural-networks/</li>
A survey on neural networks for (cyber-) security and (cyber-) security of neural networks - ScienceDirect - https://www.sciencedirect.com/science/article/pii/S0925231222007184</li>
Extremely boosted neural network for more accurate multi-stage Cyber attack prediction in cloud computing environment | Journal of Cloud Computing - https://journalofcloudcomputing.springeropen.com/articles/10.1186/s13677-022-00356-9</li>
How Effective Are Neural Networks for Fixing Security Vulnerabilities - https://arxiv.org/html/2305.18607v2</li>
[2011.05976] The Vulnerability of the Neural Networks Against Adversarial Examples in Deep Learning Algorithms - https://arxiv.org/abs/2011.05976</li>
Exploring the Security Vulnerabilities of Neural Networks - https://opendatascience.com/exploring-the-security-vulnerabilities-of-neural-networks/</li>
Machine Learning in Security: Detecting Suspicious Processes Using Recurrent Neural Networks | Splunk - https://www.splunk.com/en_us/blog/security/machine-learning-in-security-detecting-suspicious-processes-using-recurrent-neural-networks.html</li>
Security Assessment of Software Design using Neural - https://arxiv.org/pdf/1303.2017</li> </ol>

Brenner Cruvinel - segurança

Model Extraction Attacks contra Redes Neurais Black-Box (2020-2026)