paper-with-me

홈 › Papers

Provable Privacy Attacks on Trained Shallow Neural Networks

2024-10-10 · Guy Smorodinsky, Gal Vardi, Itay Safran

We study what provable privacy attacks can be shown on trained, 2-layer ReLU neural networks. We explore two types of attacks; data reconstruction attacks, and membership inference attacks. We prove that theoretical results on the implicit bias of 2-layer neural networks can be used to provably reconstruct a set of which at least a constant fraction are training points in a univariate setting, and can also be used to identify with high probability whether a given point was used in the training set in a high dimensional setting. To the best of our knowledge, our work is the first to show provable vulnerabilities in this implicit-bias-driven setting.

📄 PDF Abstract BibTeX arXiv:2410.07632

Code (1)

guy120494/Provable-Privacy-Attacks-on-Trained-Shallow-Neural-Networks 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning

2024-04-19 · Zhixin Pan, Emma Andrews, Laura Chang, Prabhat Mishra

Data augmentation is widely used to mitigate data bias in the training dataset. However, data augmentation exposes machine learning models to privacy attacks, such as membership inference attacks. In this paper, we propo…

Data AugmentationFairnessMachine UnlearningPrivacy Preserving

Evaluations of Machine Learning Privacy Defenses are Misleading

2024-04-26 · Michael Aerni, Jie Zhang, Florian Tramèr

Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries. We identify severe pitfalls in existing…

Differentially Private Instance Encoding against Privacy Attacks

2022-07-01 · NAACL (ACL) 2022 7 · Shangyu Xie, Yuan Hong

TextHide was recently proposed to protect the training data via instance encoding in natural language domain. Due to the lack of theoretic privacy guarantee, such instance encoding scheme has been shown to be vulnerable …

Reconstruction Attack

Evading classifiers in discrete domains with provable optimality guarantees

2018-10-25 · Bogdan Kulynych, Jamie Hayes, Nikita Samarin, Carmela Troncoso

Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against advers…

Adversarial RobustnessSpam detectionTwitter Bot Detectionvalid

Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness

2019-06-02 · NhatHai Phan, Minh Vu, Yang Liu, Ruoming Jin 외

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of t…