اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدQuantifying and Mitigating Privacy Risks of Contrastive Learning
34
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Data is the key factor to drive the development of machine learning (ML) during the past decade. However, high-quality data, in particular labeled data, is often hard and expensive to collect. To leverage large-scale unlabeled data, self-supervised learning, represented by contrastive learning, is introduced. The objective of contrastive learning is to map different views derived from a training sample (e.g., through data augmentation) closer in their representation space, while different views derived from different samples more distant. In this way, a contrastive model learns to generate informative representations for data samples, which are then used to perform downstream ML tasks. Recent research has shown that machine learning models are vulnerable to various privacy attacks. However, most of the current efforts concentrate on models trained with supervised learning. Meanwhile, data samples informative representations learned with contrastive learning may cause severe privacy risks as well. In this paper, we perform the first privacy analysis of contrastive learning through the lens of membership inference and attribute inference. Our experimental results show that contrastive models are less vulnerable to membership inference attacks but more vulnerable to attribute inference attacks compared to supervised models. The former is due to the fact that contrastive models are less prone to overfitting, while the latter is caused by contrastive models capability of representing data samples expressively. To remedy this situation, we propose the first privacy-preserving contrastive learning mechanism, namely Talos, relying on adversarial training. Empirical results show that Talos can successfully mitigate attribute inference risks for contrastive models while maintaining their membership privacy and model utility.
قيم البحث
اقرأ أيضاً
Secure aggregation is a critical component in federated learning, which enables the server to learn the aggregate model of the users without observing their local models. Conventionally, secure aggregation algorithms focus only on ensuring the privac
y of individual users in a single training round. We contend that such designs can lead to significant privacy leakages over multiple training rounds, due to partial user selection/participation at each round of federated learning. In fact, we empirically show that the conventional random user selection strategies for federated learning lead to leaking users individual models within number of rounds linear in the number of users. To address this challenge, we introduce a secure aggregation framework with multi-round privacy guarantees. In particular, we introduce a new metric to quantify the privacy guarantees of federated learning over multiple training rounds, and develop a structured user selection strategy that guarantees the long-term privacy of each user (over any number of training rounds). Our framework also carefully accounts for the fairness and the average number of participating users at each round. We perform several experiments on MNIST and CIFAR-10 datasets in the IID and the non-IID settings to demonstrate the performance improvement over the baseline algorithms, both in terms of privacy protection and test accuracy.
Reliably predicting potential failure risks of machine learning (ML) systems when deployed with production data is a crucial aspect of trustworthy AI. This paper introduces Risk Advisor, a novel post-hoc meta-learner for estimating failure risks and
predictive uncertainties of any already-trained black-box classification model. In addition to providing a risk score, the Risk Advisor decomposes the uncertainty estimates into aleatoric and epistemic uncertainty components, thus giving informative insights into the sources of uncertainty inducing the failures. Consequently, Risk Advisor can distinguish between failures caused by data variability, data shifts and model limitations and advise on mitigation actions (e.g., collecting more data to counter data shift). Extensive experiments on various families of black-box classification models and on real-world and synthetic datasets covering common ML failure scenarios show that the Risk Advisor reliably predicts deployment-time failure risks in all the scenarios, and outperforms strong baselines.
This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks. First, we propose to quantitatively measure the trade-off between model accuracy and privacy losses incurred by recon
struction, tracing and membership attacks. Second, we formulate reconstruction attacks as solving a noisy system of linear equations, and prove that attacks are guaranteed to be defeated if condition (2) is unfulfilled. Third, based on theoretical analysis, a novel Secret Polarization Network (SPN) is proposed to thwart privacy attacks, which pose serious challenges to existing PPDL methods. Extensive experiments showed that model accuracies are improved on average by 5-20% compared with baseline mechanisms, in regimes where data privacy are satisfactorily protected.
Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a models decisions on input data, whereas privacy is primarily concerned with protecting information about the training data. We
analyze connections between model explanations and the leakage of sensitive information about the models training set. We investigate the privacy risks of feature-based model explanations using membership inference attacks: quantifying how much model predictions plus their explanations leak information about the presence of a datapoint in the training set of a model. We extensively evaluate membership inference attacks based on feature-based model explanations, over a variety of datasets. We show that backpropagation-based explanations can leak a significant amount of information about individual training datapoints. This is because they reveal statistical information about the decision boundaries of the model about an input, which can reveal its membership. We also empirically investigate the trade-off between privacy and explanation quality, by studying the perturbation-based model explanations.
We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a users entire contribution ($m ge 1$ samp
les), providing more stringent but more realistic protection against information leaks. We show that for high-dimensional mean estimation, empirical risk minimization with smooth losses, stochastic convex optimization, and learning hypothesis class with finite metric entropy, the privacy cost decreases as $O(1/sqrt{m})$ as users provide more samples. In contrast, when increasing the number of users $n$, the privacy cost decreases at a faster $O(1/n)$ rate. We complement these results with lower bounds showing the worst-case optimality of our algorithm for mean estimation and stochastic convex optimization. Our algorithms rely on novel techniques for private mean estimation in arbitrary dimension with error scaling as the concentration radius $tau$ of the distribution rather than the entire range. Under uniform convergence, we derive an algorithm that privately answers a sequence of $K$ adaptively chosen queries with privacy cost proportional to $tau$, and apply it to solve the learning tasks we consider.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
