arXiv subjects

Sennur Ulukus

Publications and source records attributed to Sennur Ulukus.

At least 181 records · Page 10Linked to original sources

arXiv2023

Minimizing the Age of Information Over an Erasure Channel for Random Packet Arrivals With a Storage Option at the Transmitter

We consider a time slotted communication system consisting of a base station (BS) and a user. At each time slot an update packet arrives at the BS with probability $p$, and the BS successfully transmits the update packet with probability $q$ over an erasure channel. We assume that the BS has a unit size buffer where it can store an update packet upon paying a storage cost $c$. There is a trade-off between the age of information and the storage cost. We formulate this trade-off as a Markov decision process and find an optimal switching type storage policy.

cs.IT↗

arXiv2023

Age of Information of a Power Constrained Scheduler in the Presence of a Power Constrained Adversary

We consider a time slotted communication network consisting of a base station (BS), an adversary, $N$ users and $N_s$ communication channels. Both the BS and the adversary have average power constraints and the probability of successful transmission of an update packet depends on the transmission power of the BS and the blocking power of the adversary. We provide a universal lower bound for the average age for this communication network. We prove that the uniform scheduling algorithm with any feasible transmission power choosing policy is $4$ optimal; and the max-age user choosing policy is $2$ optimal. In the second part of the paper, we consider the setting where the BS chooses a transmission policy and the adversary chooses a blocking policy from the set of randomized stationary policies. We show that the Nash equilibrium point may or may not exist for this communication network. We find special cases where the Nash equilibrium always exists.

cs.IT↗

arXiv2022

Timestomping Vulnerability of Age-Sensitive Gossip Networks

We consider gossip networks consisting of a source that maintains the current version of a file, $n$ nodes that use asynchronous gossip mechanisms to disseminate fresh information in the network, and an oblivious adversary who infects the packets at a target node through data timestamp manipulation, with the intent to replace circulation of fresh packets with outdated packets in the network. We demonstrate how network topology capacitates an adversary to influence age scaling in a network. We show that in a fully connected network, a single infected node increases the expected age from $O(\log n)$ to $O(n)$. Further, we show that the optimal behavior for an adversary is to reset the timestamps of all outgoing packets to the current time and of all incoming packets to an outdated time for the infected node; thereby preventing any fresh information to go into the infected node, and facilitating acceptance of stale information out of the infected node into other network nodes. Lastly for fully connected network, we show that if an infected node contacts only a single node instead of all nodes of the network, the system age can still be degraded to $O(n)$. These show that fully connected nature of a network can be both a benefit and a detriment for information freshness; full connectivity, while enabling fast dissemination of information, also enables fast dissipation of adversarial inputs. We then analyze the unidirectional ring network, the other end of the network connectivity spectrum, where we show that the adversarial effect on age scaling of a node is limited by its distance from the adversary, and the age scaling for a large fraction of the network continues to be $O(\sqrt{n})$, unchanged from the case with no adversary. We finally support our findings with simulations.

cs.IT↗

arXiv2022

Model Segmentation for Storage Efficient Private Federated Learning with Top $r$ Sparsification

In federated learning (FL) with top $r$ sparsification, millions of users collectively train a machine learning (ML) model locally, using their personal data by only communicating the most significant $r$ fraction of updates to reduce the communication cost. It has been shown that the values as well as the indices of these selected (sparse) updates leak information about the users' personal data. In this work, we investigate different methods to carry out user-database communications in FL with top $r$ sparsification efficiently, while guaranteeing information theoretic privacy of users' personal data. These methods incur considerable storage cost. As a solution, we present two schemes with different properties that use MDS coded storage along with a model segmentation mechanism to reduce the storage cost at the expense of a controllable amount of information leakage, to perform private FL with top $r$ sparsification.

cs.IT↗

arXiv2022

Vulnerabilities of Deep Learning-Driven Semantic Communications to Backdoor (Trojan) Attacks

This paper highlights vulnerabilities of deep learning-driven semantic communications to backdoor (Trojan) attacks. Semantic communications aims to convey a desired meaning while transferring information from a transmitter to its receiver. An encoder-decoder pair that is represented by two deep neural networks (DNNs) as part of an autoencoder is trained to reconstruct signals such as images at the receiver by transmitting latent features of small size over a limited number of channel uses. In the meantime, another DNN of a semantic task classifier at the receiver is jointly trained with the autoencoder to check the meaning conveyed to the receiver. The complex decision space of the DNNs makes semantic communications susceptible to adversarial manipulations. In a backdoor (Trojan) attack, the adversary adds triggers to a small portion of training samples and changes the label to a target label. When the transfer of images is considered, the triggers can be added to the images or equivalently to the corresponding transmitted or received signals. In test time, the adversary activates these triggers by providing poisoned samples as input to the encoder (or decoder) of semantic communications. The backdoor attack can effectively change the semantic information transferred for the poisoned input samples to a target meaning. As the performance of semantic communications improves with the signal-to-noise ratio and the number of channel uses, the success of the backdoor attack increases as well. Also, increasing the Trojan ratio in training data makes the attack more successful. In the meantime, the effect of this attack on the unpoisoned input samples remains limited. Overall, this paper shows that the backdoor attack poses a serious threat to semantic communications and presents novel design guidelines to preserve the meaning of transferred information in the presence of backdoor attacks.

cs.CR↗

arXiv2022

Personalized Decentralized Multi-Task Learning Over Dynamic Communication Graphs

Decentralized and federated learning algorithms face data heterogeneity as one of the biggest challenges, especially when users want to learn a specific task. Even when personalized headers are used concatenated to a shared network (PF-MTL), aggregating all the networks with a decentralized algorithm can result in performance degradation as a result of heterogeneity in the data. Our algorithm uses exchanged gradients to calculate the correlations among tasks automatically, and dynamically adjusts the communication graph to connect mutually beneficial tasks and isolate those that may negatively impact each other. This algorithm improves the learning performance and leads to faster convergence compared to the case where all clients are connected to each other regardless of their correlations. We conduct experiments on a synthetic Gaussian dataset and a large-scale celebrity attributes (CelebA) dataset. The experiment with the synthetic data illustrates that our proposed method is capable of detecting tasks that are positively and negatively correlated. Moreover, the results of the experiments with CelebA demonstrate that the proposed method may produce significantly faster training results than fully-connected networks.

cs.LG↗

arXiv2022

Is Semantic Communications Secure? A Tale of Multi-Domain Adversarial Attacks

Semantic communications seeks to transfer information from a source while conveying a desired meaning to its destination. We model the transmitter-receiver functionalities as an autoencoder followed by a task classifier that evaluates the meaning of the information conveyed to the receiver. The autoencoder consists of an encoder at the transmitter to jointly model source coding, channel coding, and modulation, and a decoder at the receiver to jointly model demodulation, channel decoding and source decoding. By augmenting the reconstruction loss with a semantic loss, the two deep neural networks (DNNs) of this encoder-decoder pair are interactively trained with the DNN of the semantic task classifier. This approach effectively captures the latent feature space and reliably transfers compressed feature vectors with a small number of channel uses while keeping the semantic loss low. We identify the multi-domain security vulnerabilities of using the DNNs for semantic communications. Based on adversarial machine learning, we introduce test-time (targeted and non-targeted) adversarial attacks on the DNNs by manipulating their inputs at different stages of semantic communications. As a computer vision attack, small perturbations are injected to the images at the input of the transmitter's encoder. As a wireless attack, small perturbations signals are transmitted to interfere with the input of the receiver's decoder. By launching these stealth attacks individually or more effectively in a combined form as a multi-domain attack, we show that it is possible to change the semantics of the transferred information even when the reconstruction loss remains low. These multi-domain adversarial attacks pose as a serious threat to the semantics of information transfer (with larger impact than conventional jamming) and raise the need of defense methods for the safe adoption of semantic communications.

cs.CR↗

arXiv2022

Rate-Privacy-Storage Tradeoff in Federated Learning with Top $r$ Sparsification

We investigate the trade-off between rate, privacy and storage in federated learning (FL) with top $r$ sparsification, where the users and the servers in the FL system only share the most significant $r$ and $r'$ fractions, respectively, of updates and parameters in the FL process, to reduce the communication cost. We present schemes that guarantee information theoretic privacy of the values and indices of the sparse updates sent by the users at the expense of a larger storage cost. To this end, we generalize the scheme to reduce the storage cost by allowing a certain amount of information leakage. Thus, we provide the general trade-off between the communication cost, storage cost, and information leakage in private FL with top $r$ sparsification, along the lines of two proposed schemes.

cs.IT↗

arXiv2022

Hierarchical Over-the-Air FedGradNorm

Multi-task learning (MTL) is a learning paradigm to learn multiple related tasks simultaneously with a single shared network where each task has a distinct personalized header network for fine-tuning. MTL can be integrated into a federated learning (FL) setting if tasks are distributed across clients and clients have a single shared network, leading to personalized federated learning (PFL). To cope with statistical heterogeneity in the federated setting across clients which can significantly degrade the learning performance, we use a distributed dynamic weighting approach. To perform the communication between the remote parameter server (PS) and the clients efficiently over the noisy channel in a power and bandwidth-limited regime, we utilize over-the-air (OTA) aggregation and hierarchical federated learning (HFL). Thus, we propose hierarchical over-the-air (HOTA) PFL with a dynamic weighting strategy which we call HOTA-FedGradNorm. Our algorithm considers the channel conditions during the dynamic weight selection process. We conduct experiments on a wireless communication system dataset (RadComDynamic). The experimental results demonstrate that the training speed with HOTA-FedGradNorm is faster compared to the algorithms with a naive static equal weighting strategy. In addition, HOTA-FedGradNorm provides robustness against the negative channel effects by compensating for the channel conditions during the dynamic weight selection process.

cs.LG↗

arXiv2022

Private Read Update Write (PRUW) in Federated Submodel Learning (FSL): Communication Efficient Schemes With and Without Sparsification

We investigate the problem of private read update write (PRUW) in relation to private federated submodel learning (FSL), where a machine learning model is divided into multiple submodels based on the different types of data used to train the model. In PRUW, each user downloads the required submodel without revealing its index in the reading phase, and uploads the updates of the submodel without revealing the submodel index or the values of the updates in the writing phase. In this work, we first provide a basic communication efficient PRUW scheme, and study further means of reducing the communication cost via sparsification. Gradient sparsification is a widely used concept in learning applications, where only a selected set of parameters is downloaded and updated, which significantly reduces the communication cost. In this paper, we study how the concept of sparsification can be incorporated in private FSL with the goal of reducing the communication cost, while guaranteeing information theoretic privacy of the updated submodel index as well as the values of the updates. To this end, we introduce two schemes: PRUW with top $r$ sparsification and PRUW with random sparsification. The former communicates only the most significant parameters/updates among the servers and the users, while the latter communicates a randomly selected set of parameters/updates. The two proposed schemes introduce novel techniques such as parameter/update (noisy) permutations to handle the additional sources of information leakage in PRUW caused by sparsification. Both schemes result in significantly reduced communication costs compared to that of the basic (non-sparse) PRUW scheme.

cs.IT↗

arXiv2022

ASUMAN: Age Sense Updating Multiple Access in Networks

We consider a fully-connected wireless gossip network which consists of a source and $n$ receiver nodes. The source updates itself with a Poisson process and also sends updates to the nodes as Poisson arrivals. Upon receiving the updates, the nodes update their knowledge about the source. The nodes gossip the data among themselves in the form of Poisson arrivals to disperse their knowledge about the source. The total gossiping rate is bounded by a constraint. The goal of the network is to be as timely as possible with the source. In this work, we propose ASUMAN, a distributed opportunistic gossiping scheme, where after each time the source updates itself, each node waits for a time proportional to its current age and broadcasts a signal to the other nodes of the network. This allows the nodes in the network which have higher age to remain silent and only the low-age nodes to gossip, thus utilizing a significant portion of the constrained total gossip rate. We calculate the average age for a typical node in such a network with symmetric settings and show that the theoretical upper bound on the age scales as $O(1)$. ASUMAN, with an average age of $O(1)$, offers significant gains compared to a system where the nodes just gossip blindly with a fixed update rate in which case the age scales as $O(\log n)$.

cs.IT↗

arXiv2022

Rate Distortion Tradeoff in Private Read Update Write in Federated Submodel Learning

We investigate the rate distortion tradeoff in private read update write (PRUW) in relation to federated submodel learning (FSL). In FSL a machine learning (ML) model is divided into multiple submodels based on different types of data used for training. Each user only downloads and updates the submodel relevant to its local data. The process of downloading and updating the required submodel while guaranteeing privacy of the submodel index and the values of updates is known as PRUW. In this work, we study how the communication cost of PRUW can be reduced when a pre-determined amount of distortion is allowed in the reading (download) and writing (upload) phases. We characterize the rate distortion tradeoff in PRUW along with a scheme that achieves the lowest communication cost while working under a given distortion budget.

cs.IT↗

arXiv2022

Private Federated Submodel Learning with Sparsification

We investigate the problem of private read update write (PRUW) in federated submodel learning (FSL) with sparsification. In FSL, a machine learning model is divided into multiple submodels, where each user updates only the submodel that is relevant to the user's local data. PRUW is the process of privately performing FSL by reading from and writing to the required submodel without revealing the submodel index, or the values of updates to the databases. Sparsification is a widely used concept in learning, where the users update only a small fraction of parameters to reduce the communication cost. Revealing the coordinates of these selected (sparse) updates leaks privacy of the user. We show how PRUW in FSL can be performed with sparsification. We propose a novel scheme which privately reads from and writes to arbitrary parameters of any given submodel, without revealing the submodel index, values of updates, or the coordinates of the sparse updates, to databases. The proposed scheme achieves significantly lower reading and writing costs compared to what is achieved without sparsification.

cs.IT↗

arXiv2022

Dynamic SAFFRON: Disease Control Over Time Via Group Testing

We consider the dynamic infection spread model that is based on the discrete SIR model which assumes infections to be spread over time via infected and non-isolated individuals. In our system, the main objective is not to minimize the number of required tests to identify every infection, but instead, to utilize the available, given testing capacity $T$ at each time instance to efficiently control the infection spread. We introduce and study a novel performance metric, which we coin as $ε$-disease control time. This metric can be used to measure how fast a given algorithm can control the spread of a disease. We characterize the performance of dynamic individual testing algorithm and introduce a novel dynamic SAFFRON based group testing algorithm. We present theoretical results and implement the proposed algorithms to compare their performances.

eess.SY↗

arXiv2022

Susceptibility of Age of Gossip to Timestomping

We consider a fully connected network consisting of a source that maintains the current version of a file, $n$ nodes that use asynchronous gossip mechanisms to disseminate fresh information in the network, and an adversary who infects the packets at a target node through data timestamp manipulation, with the intent to replace circulation of fresh packets with outdated packets in the network. We show that a single infected node increases the expected age of a fully connected network from $O(\log n)$ to $O(n)$. Further, we show that the optimal behavior for an adversary is to reset the timestamps of all outgoing packets to the current time and of all incoming packets to an outdated time. Additionally, if the adversary allows the infected node to accept a small fraction of incoming packets from the network, then a large network can manage to curb the spread of stale files coming from the infected node and pull the network age back to $O(\log n)$. Lastly, we show that if an infected node contacts only a single node instead of all nodes of the network, the system age can still be degraded to $O(n)$. These show that fully connected nature of a network can be both a benefit and a detriment for information freshness; full connectivity, while enabling fast dissemination of information, also enables fast dissipation of adversarial inputs.

cs.IT↗

arXiv2022

Digital Blind Box: Random Symmetric Private Information Retrieval

We introduce the problem of random symmetric private information retrieval (RSPIR). In canonical PIR, a user downloads a message out of $K$ messages from $N$ non-colluding and replicated databases in such a way that no database can know which message the user has downloaded (user privacy). In SPIR, the privacy is symmetric, in that, not only that the databases cannot know which message the user has downloaded, the user itself cannot learn anything further than the particular message it has downloaded (database privacy). In RSPIR, different from SPIR, the user does not have an input to the databases, i.e., the user does not pick a specific message to download, instead is content with any one of the messages. In RSPIR, the databases need to send symbols to the user in such a way that the user is guaranteed to download a message correctly (random reliability), the databases do not know which message the user has received (user privacy), and the user does not learn anything further than the one message it has received (database privacy). This is the digital version of a blind box, also known as gachapon, which implements the above specified setting with physical objects for entertainment. This is also the blind version of $1$-out-of-$K$ oblivious transfer (OT), an important cryptographic primitive. We study the information-theoretic capacity of RSPIR for the case of $N=2$ databases. We determine its exact capacity for the cases of $K = 2, 3, 4$ messages. While we provide a general achievable scheme that is applicable to any number of messages, the capacity for $K\geq 5$ remains open.

cs.IT↗

arXiv2022

Age of Gossip in Ring Networks in the Presence of Jamming Attacks

We consider a system with a source which maintains the most current version of a file, and a ring network of $n$ user nodes that wish to acquire the latest version of the file. The source gets updated with newer file versions as a point process, and forwards them to the user nodes, which further forward them to their neighbors using a memoryless gossip protocol. We study the average version age of this network in the presence of $\tilde{n}$ jammers that disrupt inter-node communications. To this purpose, we construct an alternate system model of mini-rings and prove that the version age of the original model can be sandwiched between constant multiples of the version age of the alternate model. We show that when the number of jammers scales as a fractional power of the network size, i.e., $\tilde n= cn^α$, the version age scales as $\sqrt{n}$ when $α< \frac{1}{2}$, and as $n^α$ when $α\geq \frac{1}{2}$. As the version age of a ring network without any jammers scales as $\sqrt{n}$, our result implies that the version age with gossiping is robust against up to $\sqrt{n}$ jammers in a ring network.

cs.IT↗

arXiv2022

Group Testing with a Graph Infection Spread Model

We propose a novel infection spread model based on a random connection graph which represents connections between $n$ individuals. Infection spreads via connections between individuals and this results in a probabilistic cluster formation structure as well as a non-i.i.d. (correlated) infection status for individuals. We propose a class of two-step sampled group testing algorithms where we exploit the known probabilistic infection spread model. We investigate the metrics associated with two-step sampled group testing algorithms. To demonstrate our results, for analytically tractable exponentially split cluster formation trees, we calculate the required number of tests and the expected number of false classifications in terms of the system parameters, and identify the trade-off between them. For such exponentially split cluster formation trees, for zero-error construction, we prove that the required number of tests is $O(\log_2n)$. Thus, for such cluster formation trees, our algorithm outperforms any zero-error non-adaptive group test, binary splitting algorithm, and Hwang's generalized binary splitting algorithm. Our results imply that, by exploiting probabilistic information on the connections of individuals, group testing can be used to reduce the number of required tests significantly even when infection rate is high, contrasting the prevalent belief that group testing is useful only when infection rate is low.

cs.IT↗