اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدProbabilistic Analysis of Onion Routing in a Black-box Model
133
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We perform a probabilistic analysis of onion routing. The analysis is presented in a black-box model of anonymous communication in the Universally Composable framework that abstracts the essential properties of onion routing in the presence of an active adversary that controls a portion of the network and knows all a priori distributions on user choices of destination. Our results quantify how much the adversary can gain in identifying users by exploiting knowledge of their probabilistic behavior. In particular, we show that, in the limit as the network gets large, a user us anonymity is worst either when the other users always choose the destination u is least likely to visit or when the other users always choose the destination u chooses. This worst-case anonymity with an adversary that controls a fraction b of the routers is shown to be comparable to the best-case anonymity against an adversary that controls a fraction surdb.
قيم البحث
اقرأ أيضاً
We give a probabilistic analysis of the unit-demand Euclidean capacitated vehicle routing problem in the random setting, where the input distribution consists of $n$ unit-demand customers modeled as independent, identically distributed uniform random
points in the two-dimensional plane. The objective is to visit every customer using a set of routes of minimum total length, such that each route visits at most $k$ customers, where $k$ is the capacity of a vehicle. All of the following results are in the random setting and hold asymptotically almost surely. The best known polynomial-time approximation for this problem is the iterated tour partitioning (ITP) algorithm, introduced in 1985 by Haimovich and Rinnooy Kan. They showed that the ITP algorithm is near-optimal when $k$ is either $o(sqrt{n})$ or $omega(sqrt{n})$, and they asked whether the ITP algorithm was also effective in the intermediate range. In this work, we show that when $k=sqrt{n}$, the ITP algorithm is at best a $(1+c_0)$-approximation for some positive constant $c_0$. On the other hand, the approximation ratio of the ITP algorithm was known to be at most $0.995+alpha$ due to Bompadre, Dror, and Orlin, where $alpha$ is the approximation ratio of an algorithm for the traveling salesman problem. In this work, we improve the upper bound on the approximation ratio of the ITP algorithm to $0.915+alpha$. Our analysis is based on a new lower bound on the optimal cost for the metric capacitated vehicle routing problem, which may be of independent interest.
Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive and propri
etary training data. In this paper, we focus on one kind of model inversion attacks, where the adversary knows non-sensitive attributes about instances in the training data and aims to infer the value of a sensitive attribute unknown to the adversary, using oracle access to the target classification model. We devise two novel model inversion attribute inference attacks -- confidence modeling-based attack and confidence score-based attack, and also extend our attack to the case where some of the other (non-sensitive) attributes are unknown to the adversary. Furthermore, while previous work uses accuracy as the metric to evaluate the effectiveness of attribute inference attacks, we find that accuracy is not informative when the sensitive attribute distribution is unbalanced. We identify two metrics that are better for evaluating attribute inference attacks, namely G-mean and Matthews correlation coefficient (MCC). We evaluate our attacks on two types of machine learning models, decision tree and deep neural network, trained with two real datasets. Experimental results show that our newly proposed attacks significantly outperform the state-of-the-art attacks. Moreover, we empirically show that specific groups in the training dataset (grouped by attributes, e.g., gender, race) could be more vulnerable to model inversion attacks. We also demonstrate that our attacks performances are not impacted significantly when some of the other (non-sensitive) attributes are also unknown to the adversary.
Machine-learning-as-a-service (MLaaS) has attracted millions of users to their outperforming sophisticated models. Although published as black-box APIs, the valuable models behind these services are still vulnerable to imitation attacks. Recently, a
series of works have demonstrated that attackers manage to steal or extract the victim models. Nonetheless, none of the previous stolen models can outperform the original black-box APIs. In this work, we take the first step of showing that attackers could potentially surpass victims via unsupervised domain adaptation and multi-victim ensemble. Extensive experiments on benchmark datasets and real-world APIs validate that the imitators can succeed in outperforming the original black-box models. We consider this as a milestone in the research of imitation attack, especially on NLP APIs, as the superior performance could influence the defense or even publishing strategy of API providers.
Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively close to their originals. Last couple of years have witnessed a striking
decrease in the amount of queries a black box attack submits to the target classifier, in order to forge adversarials. This particularly concerns the black-box score-based setup, where the attacker has access to top predicted probabilites: the amount of queries went from to millions of to less than a thousand. This paper presents SurFree, a geometrical approach that achieves a similar drastic reduction in the amount of queries in the hardest setup: black box decision-based attacks (only the top-1 label is available). We first highlight that the most recent attacks in that setup, HSJA, QEBA and GeoDA all perform costly gradient surrogate estimations. SurFree proposes to bypass these, by instead focusing on careful trials along diverse directions, guided by precise indications of geometrical properties of the classifier decision boundaries. We motivate this geometric approach before performing a head-to-head comparison with previous attacks with the amount of queries as a first class citizen. We exhibit a faster distortion decay under low query amounts (few hundreds to a thousand), while remaining competitive at higher query budgets.
Machine learning models, especially neural network (NN) classifiers, have acceptable performance and accuracy that leads to their wide adoption in different aspects of our daily lives. The underlying assumption is that these models are generated and
used in attack free scenarios. However, it has been shown that neural network based classifiers are vulnerable to adversarial examples. Adversarial examples are inputs with special perturbations that are ignored by human eyes while can mislead NN classifiers. Most of the existing methods for generating such perturbations require a certain level of knowledge about the target classifier, which makes them not very practical. For example, some generators require knowledge of pre-softmax logits while others utilize prediction scores. In this paper, we design a practical black-box adversarial example generator, dubbed ManiGen. ManiGen does not require any knowledge of the inner state of the target classifier. It generates adversarial examples by searching along the manifold, which is a concise representation of input data. Through extensive set of experiments on different datasets, we show that (1) adversarial examples generated by ManiGen can mislead standalone classifiers by being as successful as the state-of-the-art white-box generator, Carlini, and (2) adversarial examples generated by ManiGen can more effectively attack classifiers with state-of-the-art defenses.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
