arXiv subjects

Amir Houmansadr

Publications and source records attributed to Amir Houmansadr.

At least 73 records · Page 4Linked to original sources

arXiv2020

Blind Adversarial Network Perturbations

Deep Neural Networks (DNNs) are commonly used for various traffic analysis problems, such as website fingerprinting and flow correlation, as they outperform traditional (e.g., statistical) techniques by large margins. However, deep neural networks are known to be vulnerable to adversarial examples: adversarial inputs to the model that get labeled incorrectly by the model due to small adversarial perturbations. In this paper, for the first time, we show that an adversary can defeat DNN-based traffic analysis techniques by applying \emph{adversarial perturbations} on the patterns of \emph{live} network traffic.

cs.CR↗

arXiv2019

Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer

Collaborative (federated) learning enables multiple parties to train a model without sharing their private data, but through repeated sharing of the parameters of their local models. Despite its advantages, this approach has many known privacy and security weaknesses and performance overhead, in addition to being limited only to models with homogeneous architectures. Shared parameters leak a significant amount of information about the local (and supposedly private) datasets. Besides, federated learning is severely vulnerable to poisoning attacks, where some participants can adversarially influence the aggregate parameters. Large models, with high dimensional parameter vectors, are in particular highly susceptible to privacy and security attacks: curse of dimensionality in federated learning. We argue that sharing parameters is the most naive way of information exchange in collaborative learning, as they open all the internal state of the model to inference attacks, and maximize the model's malleability by stealthy poisoning attacks. We propose Cronus, a robust collaborative machine learning framework. The simple yet effective idea behind designing Cronus is to control, unify, and significantly reduce the dimensions of the exchanged information between parties, through robust knowledge transfer between their black-box local models. We evaluate all existing federated learning algorithms against poisoning attacks, and we show that Cronus is the only secure method, due to its tight robustness guarantee. Treating local models as black-box, reduces the information leakage through models, and enables us using existing privacy-preserving algorithms that mitigate the risk of information leakage through the model's output (predictions). Cronus also has a significantly lower sample complexity, compared to federated learning, which does not bind its security to the number of participants.

stat.ML↗

arXiv2019

Leveraging Prior Knowledge Asymmetries in the Design of Location Privacy-Preserving Mechanisms

The prevalence of mobile devices and Location-Based Services (LBS) necessitate the study of Location Privacy-Preserving Mechanisms (LPPM). However, LPPMs reduce the utility of LBS due to the noise they add to users' locations. Here, we consider the remapping technique, which presumes the adversary has a perfect statistical model for the user location. We consider this assumption and show that under practical assumptions on the adversary's knowledge, the remapping technique leaks privacy not only about the true location data, but also about the statistical model. Finally, we introduce a novel solution called "Randomized Remapping" as a countermeasure.

cs.IT↗

arXiv2019

Privacy of Dependent Users Against Statistical Matching

Modern applications significantly enhance user experience by adapting to each user's individual condition and/or preferences. While this adaptation can greatly improve a user's experience or be essential for the application to work, the exposure of user data to the application presents a significant privacy threat to the users\textemdash even when the traces are anonymized\textemdash since the statistical matching of an anonymized trace to prior user behavior can identify a user and their habits. Because of the current and growing algorithmic and computational capabilities of adversaries, provable privacy guarantees as a function of the degree of anonymization and obfuscation of the traces are necessary. Our previous work has established the requirements on anonymization and obfuscation in the case that data traces are independent between users. However, the data traces of different users will be dependent in many applications, and an adversary can potentially exploit such. In this paper, we consider the impact of dependency between user traces on their privacy. First, we demonstrate that the adversary can readily identify the association graph of the obfuscated and anonymized version of the data, revealing which user data traces are dependent. Next, we demonstrate that the adversary can use this association graph to break user privacy with significantly shorter traces than in the case of independent users, and that obfuscating data traces independently across users is often insufficient to remedy such leakage. Finally, we discuss how users can improve privacy by employing joint obfuscation that removes or reduces the data dependency.

cs.IT↗

arXiv2019

Fundamental Limits of Invisible Flow Fingerprinting

Network flow fingerprinting can be used to de-anonymize communications on anonymity systems such as Tor by linking the ingress and egress segments of anonymized connections. Assume Alice and Bob have access to the input and the output links of an anonymous network, respectively, and they wish to collaboratively reveal the connections between the input and the output links without being detected by Willie who protects the network. Alice generates a codebook of fingerprints, where each fingerprint corresponds to a unique sequence of inter-packet delays and shares it only with Bob. For each input flow, she selects a fingerprint from the codebook and embeds it in the flow, i.e., changes the packet timings of the flow to follow the packet timings suggested by the fingerprint, and Bob extracts the fingerprints from the output flows. We model the network as parallel $M/M/1$ queues where each queue is shared by a flow from Alice to Bob and other flows independent of the flow from Alice to Bob. The timings of the flows are governed by independent Poisson point processes. Assuming all input flows have equal rates and that Bob observes only flows with fingerprints, we first present two scenarios: 1) Alice fingerprints all the flows; 2) Alice fingerprints a subset of the flows, unknown to Willie. Then, we extend the construction and analysis to the case where flow rates are arbitrary as well as the case where not all the flows that Bob observes have a fingerprint. For each scenario, we derive the number of flows that Alice can fingerprint and Bob can trace by fingerprinting.

cs.NI↗

arXiv2019

Fundamental Limits of Covert Packet Insertion

Covert communication conceals the existence of the transmission from a watchful adversary. We consider the fundamental limits for covert communications via packet insertion over packet channels whose packet timings are governed by a renewal process of rate $λ$. Authorized transmitter Jack sends packets to authorized receiver Steve, and covert transmitter Alice wishes to transmit packets to covert receiver Bob without being detected by watchful adversary Willie. Willie cannot authenticate the source of the packets. Hence, he looks for statistical anomalies in the packet stream from Jack to Steve to attempt detection of unauthorized packet insertion. First, we consider a special case where the packet timings are governed by a Poisson process and we show that Alice can covertly insert $\mathcal{O}(\sqrt{λT})$ packets for Bob in a time interval of length $T$; conversely, if Alice inserts $ω(\sqrt{λT})$, she will be detected by Willie with high probability. Then, we extend our results to general renewal channels and show that in a stream of $N$ packets transmitted by Jack, Alice can covertly insert $\mathcal{O}(\sqrt{N})$ packets; if she inserts $ω(\sqrt{N})$ packets, she will be detected by Willie with high probability.

cs.CR↗

arXiv2019

Asymptotic Loss in Privacy due to Dependency in Gaussian Traces

The rapid growth of the Internet of Things (IoT) necessitates employing privacy-preserving techniques to protect users' sensitive information. Even when user traces are anonymized, statistical matching can be employed to infer sensitive information. In our previous work, we have established the privacy requirements for the case that the user traces are instantiations of discrete random variables and the adversary knows only the structure of the dependency graph, i.e., whether each pair of users is connected. In this paper, we consider the case where data traces are instantiations of Gaussian random variables and the adversary knows not only the structure of the graph but also the pairwise correlation coefficients. We establish the requirements on anonymization to thwart such statistical matching, which demonstrate the significant degree to which knowledge of the pairwise correlation coefficients further significantly aids the adversary in breaking user anonymity.

cs.IT↗

arXiv2019

Asymptotic Limits of Privacy in Bayesian Time Series Matching

Various modern and highly popular applications make use of user data traces in order to offer specific services, often for the purpose of improving the user's experience while using such applications. However, even when user data is privatized by employing privacy-preserving mechanisms (PPM), users' privacy may still be compromised by an external party who leverages statistical matching methods to match users' traces with their previous activities. In this paper, we obtain the theoretical bounds on user privacy for situations in which user traces are matchable to sequences of prior behavior, despite anonymization of data time series. We provide both achievability and converse results for the case where the data trace of each user consists of independent and identically distributed (i.i.d.) random samples drawn from a multinomial distribution, as well as the case that the users' data points are dependent over time and the data trace of each user is governed by a Markov chain model.

cs.IT↗

arXiv2018

Fundamental Limits of Covert Bit Insertion in Packets

Covert communication is necessary when revealing the mere existence of a message leaks sensitive information to an attacker. Consider a network link where an authorized transmitter Jack sends packets to an authorized receiver Steve, and the packets visit Alice, Willie, and Bob, respectively, before they reach Steve. Covert transmitter Alice wishes to alter the packet stream in some way to send information to covert receiver Bob without watchful and capable adversary Willie being able to detect the presence of the message. In our previous works, we addressed two techniques for such covert transmission from Alice to Bob: packet insertion and packet timing. In this paper, we consider covert communication via bit insertion in packets with available space (e.g., with size less than the maximum transmission unit). We consider three scenarios: 1) packet sizes are independent and identically distributed (i.i.d.) with a probability mass function (pmf) whose support is a set of one bit spaced values; 2) packet sizes are i.i.d. with a pmf whose support is arbitrary; 3) packet sizes may be dependent. For the first and second assumptions, we show that Alice can covertly insert $\mathcal{O}(\sqrt{n})$ bits of information in a flow of $n$ packets; conversely, if she inserts $ω(\sqrt{n})$ bits of information, Willie can detect her with arbitrarily small error probability. For the third assumption, we prove Alice can covertly insert on average $\mathcal{O}(c(n)/\sqrt{n})$ bits in a sequence of $n$ packets, where $c(n)$ is the average number of conditional pmf of packet sizes given the history, with a support of at least size two.

cs.NI↗

arXiv2018

Towards Provably Invisible Network Flow Fingerprints

Network traffic analysis reveals important information even when messages are encrypted. We consider active traffic analysis via flow fingerprinting by invisibly embedding information into packet timings of flows. In particular, assume Alice wishes to embed fingerprints into flows of a set of network input links, whose packet timings are modeled by Poisson processes, without being detected by a watchful adversary Willie. Bob, who receives the set of fingerprinted flows after they pass through the network modeled as a collection of independent and parallel $M/M/1$ queues, wishes to extract Alice's embedded fingerprints to infer the connection between input and output links of the network. We consider two scenarios: 1) Alice embeds fingerprints in all of the flows; 2) Alice embeds fingerprints in each flow independently with probability $p$. Assuming that the flow rates are equal, we calculate the maximum number of flows in which Alice can invisibly embed fingerprints while having those fingerprints successfully decoded by Bob. Then, we extend the construction and analysis to the case where flow rates are distinct, and discuss the extension of the network model.

cs.NI↗

arXiv2018

DeepCorr: Strong Flow Correlation Attacks on Tor Using Deep Learning

Flow correlation is the core technique used in a multitude of deanonymization attacks on Tor. Despite the importance of flow correlation attacks on Tor, existing flow correlation techniques are considered to be ineffective and unreliable in linking Tor flows when applied at a large scale, i.e., they impose high rates of false positive error rates or require impractically long flow observations to be able to make reliable correlations. In this paper, we show that, unfortunately, flow correlation attacks can be conducted on Tor traffic with drastically higher accuracies than before by leveraging emerging learning mechanisms. We particularly design a system, called DeepCorr, that outperforms the state-of-the-art by significant margins in correlating Tor connections. DeepCorr leverages an advanced deep learning architecture to learn a flow correlation function tailored to Tor's complex network this is in contrast to previous works' use of generic statistical correlation metrics to correlated Tor flows. We show that with moderate learning, DeepCorr can correlate Tor connections (and therefore break its anonymity) with accuracies significantly higher than existing algorithms, and using substantially shorter lengths of flow observations. For instance, by collecting only about 900 packets of each target Tor flow (roughly 900KB of Tor data), DeepCorr provides a flow correlation accuracy of 96% compared to 4% by the state-of-the-art system of RAPTOR using the same exact setting. We hope that our work demonstrates the escalating threat of flow correlation attacks on Tor given recent advances in learning algorithms, calling for the timely deployment of effective countermeasures by the Tor community.

cs.CR↗

arXiv2018

Machine Learning with Membership Privacy using Adversarial Regularization

Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to distinguish between data points that were part of the model's training set and any other data points from the same distribution. This is known as the tracing (and also membership inference) attack. In this paper, we focus on such attacks against black-box models, where the adversary can only observe the output of the model, but not its parameters. This is the current setting of machine learning as a service in the Internet. We introduce a privacy mechanism to train machine learning models that provably achieve membership privacy: the model's predictions on its training data are indistinguishable from its predictions on other data points from the same distribution. We design a strategic mechanism where the privacy mechanism anticipates the membership inference attacks. The objective is to train a model such that not only does it have the minimum prediction error (high utility), but also it is the most robust model against its corresponding strongest inference attack (high privacy). We formalize this as a min-max game optimization problem, and design an adversarial training algorithm that minimizes the classification loss of the model as well as the maximum gain of the membership inference attack against it. This strategy, which guarantees membership privacy (as prediction indistinguishability), acts also as a strong regularizer and significantly generalizes the model. We evaluate our privacy mechanism on deep neural networks using different benchmark datasets. We show that our min-max strategy can mitigate the risk of membership inference attacks (close to the random guess) with a negligible cost in terms of the classification error.

stat.ML↗

arXiv2018

Matching Anonymized and Obfuscated Time Series to Users' Profiles

Many popular applications use traces of user data to offer various services to their users. However, even if user data is anonymized and obfuscated, a user's privacy can be compromised through the use of statistical matching techniques that match a user trace to prior user behavior. In this work, we derive the theoretical bounds on the privacy of users in such a scenario. We build on our recent study in the area of location privacy, in which we introduced formal notions of location privacy for anonymization-based location privacy-protection mechanisms. Here we derive the fundamental limits of user privacy when both anonymization and obfuscation-based protection mechanisms are applied to users' time series of data. We investigate the impact of such mechanisms on the trade-off between privacy protection and user utility. We first study achievability results for the case where the time-series of users are governed by an i.i.d. process. The converse results are proved both for the i.i.d. case as well as the more general Markov chain model. We demonstrate that as the number of users in the network grows, the obfuscation-anonymization plane can be divided into two regions: in the first region, all users have perfect privacy; and, in the second region, no user has privacy.

cs.IT↗

arXiv2018

Privacy against Statistical Matching: Inter-User Correlation

Modern applications significantly enhance user experience by adapting to each user's individual condition and/or preferences. While this adaptation can greatly improve utility or be essential for the application to work (e.g., for ride-sharing applications), the exposure of user data to the application presents a significant privacy threat to the users, even when the traces are anonymized, since the statistical matching of an anonymized trace to prior user behavior can identify a user and their habits. Because of the current and growing algorithmic and computational capabilities of adversaries, provable privacy guarantees as a function of the degree of anonymization and obfuscation of the traces are necessary. Our previous work has established the requirements on anonymization and obfuscation in the case that data traces are independent between users. However, the data traces of different users will be dependent in many applications, and an adversary can potentially exploit such. In this paper, we consider the impact of correlation between user traces on their privacy. First, we demonstrate that the adversary can readily identify the association graph, revealing which user data traces are correlated. Next, we demonstrate that the adversary can use this association graph to break user privacy with significantly shorter traces than in the case when traces are independent between users, and that independent obfuscation of the data traces is often insufficient to remedy such. Finally, we discuss how the users can employ dependency in their obfuscation to improve their privacy.

cs.IT↗

arXiv2017

Covert Communications on Renewal Packet Channels

Security and privacy are major concerns in modern communication networks. In recent years, the information theory of covert communications, where the very presence of the communication is undetectable to a watchful and determined adversary, has been of great interest. This emerging body of work has focused on additive white Gaussian noise (AWGN), discrete memoryless channels (DMCs), and optical channels. In contrast, our recent work introduced the information-theoretic limits for covert communications over packet channels whose packet timings are governed by a Poisson point process. However, actual network packet arrival times do not generally conform to the Poisson process assumption, and thus here we consider the extension of our work to timing channels characterized by more general renewal processes of rate $λ$. We consider two scenarios. In the first scenario, the source of the packets on the channel cannot be authenticated by Willie, and therefore Alice can insert packets into the channel. We show that if the total number of transmitted packets by Jack is $N$, Alice can covertly insert $\mathcal{O}\left(\sqrt{N}\right)$ packets and, if she transmits more, she will be detected by Willie. In the second scenario, packets are authenticated by Willie but we assume that Alice and Bob share a secret key; hence, Alice alters the timings of the packets according to a pre-shared codebook with Bob to send information to him over a $G/M/1$ queue with service rate $μ>λ$. We show that Alice can covertly and reliably transmit $\mathcal{O}(N)$ bits to Bob when the total number of packets sent from Jack to Steve is $N$.

cs.IT↗

arXiv2017

Covert Communications on Poisson Packet Channels

Consider a channel where authorized transmitter Jack sends packets to authorized receiver Steve according to a Poisson process with rate $λ$ packets per second for a time period $T$. Suppose that covert transmitter Alice wishes to communicate information to covert receiver Bob on the same channel without being detected by a watchful adversary Willie. We consider two scenarios. In the first scenario, we assume that warden Willie cannot look at packet contents but rather can only observe packet timings, and Alice must send information by inserting her own packets into the channel. We show that the number of packets that Alice can covertly transmit to Bob is on the order of the square root of the number of packets that Jack transmits to Steve; conversely, if Alice transmits more than that, she will be detected by Willie with high probability. In the second scenario, we assume that Willie can look at packet contents but that Alice can communicate across an $M/M/1$ queue to Bob by altering the timings of the packets going from Jack to Steve. First, Alice builds a codebook, with each codeword consisting of a sequence of packet timings to be employed for conveying the information associated with that codeword. However, to successfully employ this codebook, Alice must always have a packet to send at the appropriate time. Hence, leveraging our result from the first scenario, we propose a construction where Alice covertly slows down the packet stream so as to buffer packets to use during a succeeding codeword transmission phase. Using this approach, Alice can covertly and reliably transmit $\mathcal{O}(λT)$ covert bits to Bob in time period $T$ over an $M/M/1$ queue with service rate $μ> λ$.

cs.IT↗

arXiv2017

Enemy At the Gateways: A Game Theoretic Approach to Proxy Distribution

A core technique used by popular proxy-based circumvention systems like Tor, Psiphon, and Lantern is to secretly share the IP addresses of circumvention proxies with the censored clients for them to be able to use such systems. For instance, such secretly shared proxies are known as bridges in Tor. However, a key challenge to this mechanism is the insider attack problem: censoring agents can impersonate as benign censored clients in order to obtain (and then block) such secretly shared circumvention proxies. In this paper, we perform a fundamental study on the problem of insider attack on proxy-based circumvention systems. We model the proxy distribution problem using game theory, based on which we derive the optimal strategies of the parties involved, i.e., the censors and circumvention system operators. That is, we derive the optimal proxy distribution mechanism of a circumvention system like Tor, against the censorship adversary who also takes his optimal censorship strategies. This is unlike previous works that design ad hoc mechanisms for proxy distribution, against non-optimal censors. We perform extensive simulations to evaluate our optimal proxy assignment algorithm under various adversarial and network settings. Comparing with the state-of-the-art prior work, we show that our optimal proxy assignment algorithm has superior performance, i.e., better resistance to censorship even against the strongest censorship adversary who takes her optimal actions. We conclude with lessons and recommendation for the design of proxy-based circumvention systems.

cs.CR↗

arXiv2017

Achieving Perfect Location Privacy in Wireless Devices Using Anonymization

The popularity of mobile devices and location-based services (LBS) has created great concern regarding the location privacy of their users. Anonymization is a common technique that is often used to protect the location privacy of LBS users. Here, we present an information-theoretic approach to define the notion of perfect location privacy. We show how LBS's should use the anonymization method to ensure that their users can achieve perfect location privacy. First, we assume that a user's current location is independent from her past locations. Using this i.i.d model, we show that if the pseudonym of the user is changed before $O(n^{\frac{2}{r-1}})$ observations are made by the adversary for that user, then the user has perfect location privacy. Here, n is the number of the users in the network and r is the number of all possible locations that users can go to. Next, we model users' movements using Markov chains to better model real-world movement patterns. We show that perfect location privacy is achievable for a user if the user's pseudonym is changed before $O(n^{\frac{2}{|E|-r}})$ observations are collected by the adversary for the user, where |E| is the number of edges in the user's Markov chain model.

cs.IT↗