اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدWhere Did You Learn That From? Surprising Effectiveness of Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning
138
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
While significant research advances have been made in the field of deep reinforcement learning, a major challenge to widespread industrial adoption of deep reinforcement learning that has recently surfaced but little explored is the potential vulnerability to privacy breaches. In particular, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to membership inference attacks. To address this gap, we propose an adversarial attack framework tailored for testing the vulnerability of deep reinforcement learning algorithms to membership inference attacks. More specifically, we design a series of experiments to investigate the impact of temporal correlation, which naturally exists in reinforcement learning training data, on the probability of information leakage. Furthermore, we study the differences in the performance of emph{collective} and emph{individual} membership attacks against deep reinforcement learning algorithms. Experimental results show that the proposed adversarial attack framework is surprisingly effective at inferring the data used during deep reinforcement training with an accuracy exceeding $84%$ in individual and $97%$ in collective mode on two different control tasks in OpenAI Gym, which raises serious privacy concerns in the deployment of models resulting from deep reinforcement learning. Moreover, we show that the learning state of a reinforcement learning algorithm significantly influences the level of the privacy breach.
قيم البحث
اقرأ أيضاً
Membership inference attack aims to identify whether a data sample was used to train a machine learning model or not. It can raise severe privacy risks as the membership can reveal an individuals sensitive information. For example, identifying an ind
ividuals participation in a hospitals health analytics training set reveals that this individual was once a patient in that hospital. Membership inference attacks have been shown to be effective on various machine learning models, such as classification models, generative models, and sequence-to-sequence models. Meanwhile, many methods are proposed to defend such a privacy attack. Although membership inference attack is an emerging and rapidly growing research area, there is no comprehensive survey on this topic yet. In this paper, we bridge this important gap in membership inference attack literature. We present the first comprehensive survey of membership inference attacks. We summarize and categorize existing membership inference attacks and defenses and explicitly present how to implement attacks in various settings. Besides, we discuss why membership inference attacks work and summarize the benchmark datasets to facilitate comparison and ensure fairness of future work. Finally, we propose several possible directions for future research and possible applications relying on reviewed works.
A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the models training data or not. In this paper, we provide an in-depth study of the phenomenon of disparate
vulnerability against MIAs: unequal success rate of MIAs against different population subgroups. We first establish necessary and sufficient conditions for MIAs to be prevented, both on average and for population subgroups, using a notion of distributional generalization. Second, we derive connections of disparate vulnerability to algorithmic fairness and to differential privacy. We show that fairness can only prevent disparate vulnerability against limited classes of adversaries. Differential privacy bounds disparate vulnerability but can significantly reduce the accuracy of the model. We show that estimating disparate vulnerability to MIAs by naively applying existing attacks can lead to overestimation. We then establish which attacks are suitable for estimating disparate vulnerability, and provide a statistical framework for doing so reliably. We conduct experiments on synthetic and real-world data finding statistically significant evidence of disparate vulnerability in realistic settings.
Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such synthetic data can be used for a variety of downstream tasks such as tr
aining classifiers that would otherwise require the original dataset to be shared. However, recent work has shown that the GAN models and their synthetically generated data can be used to infer the training set membership by an adversary who has access to the entire dataset and some auxiliary information. Current approaches to mitigate this problem (such as DPGAN) lead to dramatically poorer generated sample quality than the original non--private GANs. Here we develop a new GAN architecture (privGAN), where the generator is trained not only to cheat the discriminator but also to defend membership inference attacks. The new mechanism provides protection against this mode of attack while leading to negligible loss in downstream performances. In addition, our algorithm has been shown to explicitly prevent overfitting to the training set, which explains why our protection is so effective. The main contributions of this paper are: i) we propose a novel GAN architecture that can generate synthetic data in a privacy preserving manner without additional hyperparameter tuning and architecture selection, ii) we provide a theoretical understanding of the optimal solution of the privGAN loss function, iii) we demonstrate the effectiveness of our model against several white and black--box attacks on several benchmark datasets, iv) we demonstrate on three common benchmark datasets that synthetic images generated by privGAN lead to negligible loss in downstream performance when compared against non--private GANs.
Recent work has discovered that deep reinforcement learning (DRL) policies are vulnerable to adversarial examples. These attacks mislead the policy of DRL agents by perturbing the state of the environment observed by agents. They are feasible in prin
ciple but too slow to fool DRL policies in real time. We propose a new attack to fool DRL policies that is both effective and efficient enough to be mounted in real time. We utilize the Universal Adversarial Perturbation (UAP) method to compute effective perturbations independent of the individual inputs to which they are applied. Via an extensive evaluation using Atari 2600 games, we show that our technique is effective, as it fully degrades the performance of both deterministic and stochastic policies (up to 100%, even when the $l_infty$ bound on the perturbation is as small as 0.005). We also show that our attack is efficient, incurring an online computational cost of 0.027ms on average. It is faster compared to the response time (0.6ms on average) of agents with different DRL policies, and considerably faster than prior attacks (2.7ms on average). Furthermore, we demonstrate that known defenses are ineffective against universal perturbations. We propose an effective detection technique which can form the basis for robust defenses against attacks based on universal perturbations.
Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from recommender sys
tems may lead to severe privacy problems. In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference. In contrast with traditional membership inference against machine learning classifiers, our attack faces two main differences. First, our attack is on the user-level but not on the data sample-level. Second, the adversary can only observe the ordered recommended items from a recommender system instead of prediction results in the form of posterior probabilities. To address the above challenges, we propose a novel method by representing users from relevant items. Moreover, a shadow recommender is established to derive the labeled training data for training the attack model. Extensive experimental results show that our attack framework achieves a strong performance. In addition, we design a defense mechanism to effectively mitigate the membership inference threat of recommender systems.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
