اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدEnabling Inference Privacy with Adaptive Noise Injection
55
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
User-facing software services are becoming increasingly reliant on remote servers to host Deep Neural Network (DNN) models, which perform inference tasks for the clients. Such services require the client to send input data to the service provider, who processes it using a DNN and returns the output predictions to the client. Due to the rich nature of the inputs such as images and speech, the input often contains more information than what is necessary to perform the primary inference task. Consequently, in addition to the primary inference task, a malicious service provider could infer secondary (sensitive) attributes from the input, compromising the clients privacy. The goal of our work is to improve inference privacy by injecting noise to the input to hide the irrelevant features that are not conducive to the primary classification task. To this end, we propose Adaptive Noise Injection (ANI), which uses a light-weight DNN on the client-side to inject noise to each input, before transmitting it to the service provider to perform inference. Our key insight is that by customizing the noise to each input, we can achieve state-of-the-art trade-off between utility and privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy), significantly outperforming existing noise injection schemes. Our method does not require prior knowledge of the sensitive attributes and incurs minimal computational overheads.
قيم البحث
اقرأ أيضاً
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique contributions. First, t
hrough MPLens, we demonstrate how membership inference attack methods can be leveraged in adversarial machine learning. Second, through MPLens, we highlight how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data itself is skewed. We show that risk from membership inference attacks is routinely increased when models use skewed training data. Finally, we investigate the effectiveness of differential privacy as a mitigation technique against membership inference attacks. We discuss the trade-offs of implementing such a mitigation strategy with respect to the model complexity, the learning task complexity, the dataset complexity and the privacy parameter settings. Our empirical results reveal that (1) minority groups within skewed datasets display increased risk for membership inference and (2) differential privacy presents many challenging trade-offs as a mitigation technique to membership inference risk.
The infection rate of COVID-19 and lack of an approved vaccine has forced governments and health authorities to adopt lockdowns, increased testing, and contact tracing to reduce the spread of the virus. Digital contact tracing has become a supplement
to the traditional manual contact tracing process. However, although there have been a number of digital contact tracing apps proposed and deployed, these have not been widely adopted owing to apprehensions surrounding privacy and security. In this paper, we propose a blockchain-based privacy-preserving contact tracing protocol, Did I Meet You (DIMY), that provides full-lifecycle data privacy protection on the devices themselves as well as on the back-end servers, to address most of the privacy concerns associated with existing protocols. We have employed Bloom filters to provide efficient privacy-preserving storage, and have used the Diffie-Hellman key exchange for secret sharing among the participants. We show that DIMY provides resilience against many well known attacks while introducing negligible overheads. DIMYs footprint on the storage space of clients devices and back-end servers is also significantly lower than other similar state of the art apps.
Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense techniques were p
roposed. However, existing defense techniques often require modifying the target model or depend on the prior knowledge of attacks. In this paper, we propose a straightforward method for detecting adversarial image examples, which can be directly deployed into unmodified off-the-shelf DNN models. We consider the perturbation to images as a kind of noise and introduce two classic image processing techniques, scalar quantization and smoothing spatial filter, to reduce its effect. The image entropy is employed as a metric to implement an adaptive noise reduction for different kinds of images. Consequently, the adversarial example can be effectively detected by comparing the classification results of a given sample and its denoised version, without referring to any prior knowledge of attacks. More than 20,000 adversarial examples against some state-of-the-art DNN models are used to evaluate the proposed method, which are crafted with different attack techniques. The experiments show that our detection method can achieve a high overall F1 score of 96.39% and certainly raises the bar for defense-aware attacks.
Point-of-Interest (POI) recommendation has been extensively studied and successfully applied in industry recently. However, most existing approaches build centralized models on the basis of collecting users data. Both private data and models are held
by the recommender, which causes serious privacy concerns. In this paper, we propose a novel Privacy preserving POI Recommendation (PriRec) framework. First, to protect data privacy, users private data (features and actions) are kept on their own side, e.g., Cellphone or Pad. Meanwhile, the public data need to be accessed by all the users are kept by the recommender to reduce the storage costs of users devices. Those public data include: (1) static data only related to the status of POI, such as POI categories, and (2) dynamic data depend on user-POI actions such as visited counts. The dynamic data could be sensitive, and we develop local differential privacy techniques to release such data to public with privacy guarantees. Second, PriRec follows the representations of Factorization Machine (FM) that consists of linear model and the feature interaction model. To protect the model privacy, the linear models are saved on users side, and we propose a secure decentralized gradient descent protocol for users to learn it collaboratively. The feature interaction model is kept by the recommender since there is no privacy risk, and we adopt secure aggregation strategy in federated learning paradigm to learn it. To this end, PriRec keeps users private raw data and models in users own hands, and protects user privacy to a large extent. We apply PriRec in real-world datasets, and comprehensive experiments demonstrate that, compared with FM, PriRec achieves comparable or even better recommendation accuracy.
Dropout is a regularisation technique in neural network training where unit activations are randomly set to zero with a given probability emph{independently}. In this work, we propose a generalisation of dropout and other multiplicative noise injecti
on schemes for shallow and deep neural networks, where the random noise applied to different units is not independent but follows a joint distribution that is either fixed or estimated during training. We provide theoretical insights on why such adaptive structured noise injection (ASNI) may be relevant, and empirically confirm that it helps boost the accuracy of simple feedforward and convolutional neural networks, disentangles the hidden layer representations, and leads to sparser representations. Our proposed method is a straightforward modification of the classical dropout and does not require additional computational overhead.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
