arXiv subjects

Aylin Yener

Publications and source records attributed to Aylin Yener.

At least 55 records · Page 3Linked to original sources

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

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

Iterative Power Control for Wireless Networks with Distributed Reconfigurable Intelligent Surfaces

Reconfigurable Intelligent Surfaces (RIS) are a new paradigm which, with judicious deployment and alignment, can enable more favorable propagation environments and better wireless network design. As such, they can offer a number of potential benefits for next generation wireless systems including improved coverage, better interference management and even security. In this paper, we consider an uplink next generation wireless system where each user is assisted with an RIS. We study the uplink power control problem in this distributed RIS-assisted wireless network. Specifically, we aim to minimize total uplink transmit power of all the users subject to each user's reliable communication requirements at the base station by a joint design of power, receiver filter and RIS phase matrices. We propose an iterative power control algorithm, combined with a successive convex approximation technique to solve the problem with non-convex phase constraints. Numerical results illustrate that distributed RIS assistance leads to uplink power savings when direct links are weak.

cs.IT↗

arXiv2022

Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications

Communication systems to date primarily aim at reliably communicating bit sequences. Such an approach provides efficient engineering designs that are agnostic to the meanings of the messages or to the goal that the message exchange aims to achieve. Next generation systems, however, can be potentially enriched by folding message semantics and goals of communication into their design. Further, these systems can be made cognizant of the context in which communication exchange takes place, providing avenues for novel design insights. This tutorial summarizes the efforts to date, starting from its early adaptations, semantic-aware and task-oriented communications, covering the foundations, algorithms and potential implementations. The focus is on approaches that utilize information theory to provide the foundations, as well as the significant role of learning in semantics and task-aware communications.

cs.IT↗

arXiv2022

Secure Joint Communication and Sensing

This work considers the problem of mitigating information leakage between communication and sensing in systems jointly performing both operations. Specifically, a discrete memoryless state-dependent broadcast channel model is studied in which (i) the presence of feedback enables a transmitter to convey information, while simultaneously performing channel state estimation; (ii) one of the receivers is treated as an eavesdropper whose state should be estimated but which should remain oblivious to part of the transmitted information. The model abstracts the challenges behind security for joint communication and sensing if one views the channel state as a sensitive attribute, e.g., location. For independent and identically distributed states, perfect output feedback, and when part of the transmitted message should be kept secret, a partial characterization of the secrecy-distortion region is developed. The characterization is exact when the broadcast channel is either physically-degraded or reversely-physically-degraded. The partial characterization is also extended to the situation in which the entire transmitted message should be kept secret. The benefits of a joint approach compared to separation-based secure communication and state-sensing methods are illustrated with a binary joint communication and sensing model.

cs.IT↗

arXiv2022

CHARLES: Channel-Quality-Adaptive Over-the-Air Federated Learning over Wireless Networks

Over-the-air federated learning (OTA-FL) has emerged as an efficient mechanism that exploits the superposition property of the wireless medium and performs model aggregation for federated learning in the air. OTA-FL is naturally sensitive to wireless channel fading, which could significantly diminish its learning accuracy. To address this challenge, in this paper, we propose an OTA-FL algorithm called CHARLES (channel-quality-aware over-the-air local estimating and scaling). Our CHARLES algorithm performs channel state information (CSI) estimation and adaptive scaling to mitigate the impacts of wireless channel fading. We establish the theoretical convergence rate performance of CHARLES and analyze the impacts of CSI error on the convergence of CHARLES. We show that the adaptive channel inversion scaling scheme in CHARLES is robust under imperfect CSI scenarios. We also demonstrate through numerical results that CHARLES outperforms existing OTA-FL algorithms with heterogeneous data under imperfect CSI.

cs.IT↗

arXiv2022

Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control

This paper considers over-the-air federated learning (OTA-FL). OTA-FL exploits the superposition property of the wireless medium, and performs model aggregation over the air for free. Thus, it can greatly reduce the communication cost incurred in communicating model updates from the edge devices. In order to fully utilize this advantage while providing comparable learning performance to conventional federated learning that presumes model aggregation via noiseless channels, we consider the joint design of transmission scaling and the number of local iterations at each round, given the power constraint at each edge device. We first characterize the training error due to such channel noise in OTA-FL by establishing a fundamental lower bound for general functions with Lipschitz-continuous gradients. Then, by introducing an adaptive transceiver power scaling scheme, we propose an over-the-air federated learning algorithm with joint adaptive computation and power control (ACPC-OTA-FL). We provide the convergence analysis for ACPC-OTA-FL in training with non-convex objective functions and heterogeneous data. We show that the convergence rate of ACPC-OTA-FL matches that of FL with noise-free communications.

cs.LG↗

arXiv2022

State Amplification and Masking While Timely Updating

In status update systems, multiple features carried by the status updating process require pursuit of objectives beyond timeliness measured by the age of information of updates. We consider such a problem where the transmitter sends status update messages through a noiseless binary energy harvesting channel that is equivalent to a timing channel. The transmitter aims to amplify or mask the energy state information that is carried in the updating process. The receiver extracts encoded information, infers the energy state sequence while maintaining timeliness of status updates. Consequently, the timings of the updates must be designed to control the message rate, the energy state uncertainty, and the age of information. We investigate this three-way trade-off between the achievable rate, the reduction in energy arrival state uncertainty, and the age of information, for zero and infinite battery cases.

cs.IT↗

arXiv2021

Autoencoder-based Communications with Reconfigurable Intelligent Surfaces

This paper presents a novel approach for the joint design of a reconfigurable intelligent surface (RIS) and a transmitter-receiver pair that are trained together as a set of deep neural networks (DNNs) to optimize the end-to-end communication performance at the receiver. The RIS is a software-defined array of unit cells that can be controlled in terms of the scattering and reflection profiles to focus the incoming signals from the transmitter to the receiver. The benefit of the RIS is to improve the coverage and spectral efficiency for wireless communications by overcoming physical obstructions of the line-of-sight (LoS) links. The selection process of the RIS beam codeword (out of a pre-defined codebook) is formulated as a DNN, while the operations of the transmitter-receiver pair are modeled as two DNNs, one for the encoder (at the transmitter) and the other one for the decoder (at the receiver) of an autoencoder, by accounting for channel effects including those induced by the RIS in between. The underlying DNNs are jointly trained to minimize the symbol error rate at the receiver. Numerical results show that the proposed design achieves major gains in error performance with respect to various baseline schemes, where no RIS is used or the selection of the RIS beam is separated from the design of the transmitter-receiver pair.

cs.NI↗

arXiv2021

Universal Covertness for Discrete Memoryless Sources

Consider a sequence $X^n$ of length $n$ emitted by a Discrete Memoryless Source (DMS) with unknown distribution $p_X$. The objective is to construct a lossless source code that maps $X^n$ to a sequence $\widehat{Y}^m$ of length $m$ that is indistinguishable, in terms of Kullback-Leibler divergence, from a sequence emitted by another DMS with known distribution $p_Y$. The main result is the existence of a coding scheme that performs this task with an optimal ratio $m/n$ equal to $H(X)/H(Y)$, the ratio of the Shannon entropies of the two distributions, as $n$ goes to infinity. The coding scheme overcomes the challenges created by the lack of knowledge about $p_X$ by a type-based universal lossless source coding scheme that produces as output an almost uniformly distributed sequence, followed by another type-based coding scheme that jointly performs source resolvability and universal lossless source coding. The result recovers and extends previous results that either assume $p_X$ or $p_Y$ uniform, or $p_X$ known. The price paid for these generalizations is the use of common randomness with vanishing rate, whose length scales as the logarithm of $n$. By allowing common randomness larger than the logarithm of $n$ but still negligible compared to $n$, a constructive low-complexity encoding and decoding counterpart to the main result is also provided for binary sources by means of polar codes.

cs.IT↗

arXiv2021

Sustainable Federated Learning

Potential environmental impact of machine learning by large-scale wireless networks is a major challenge for the sustainability of future smart ecosystems. In this paper, we introduce sustainable machine learning in federated learning settings, using rechargeable devices that can collect energy from the ambient environment. We propose a practical federated learning framework that leverages intermittent energy arrivals for training, with provable convergence guarantees. Our framework can be applied to a wide range of machine learning settings in networked environments, including distributed and federated learning in wireless and edge networks. Our experiments demonstrate that the proposed framework can provide significant performance improvement over the benchmark energy-agnostic federated learning settings.

cs.LG↗

arXiv2021

Coded Caching in the Presence of a Wire and a Cache Tapping Adversary of Type II

This paper introduces the notion of cache-tapping into the information theoretic models of coded caching. The wiretap channel II in the presence of multiple receivers equipped with fixed-size cache memories, and an adversary which selects symbols to tap into from cache placement and/or delivery is introduced. The legitimate terminals know neither whether placement, delivery, or both are tapped, nor the positions in which they are tapped. Only the size of the overall tapped set is known. For two receivers and two files, the strong secrecy capacity -- the maximum achievable file rate while keeping the overall library strongly secure -- is identified. Lower and upper bounds on the strong secrecy file rate are derived when the library has more than two files. Achievability relies on a code design which combines wiretap coding, security embedding codes, one-time pad keys, and coded caching. A genie-aided upper bound, in which the transmitter is provided with user demands before placement, establishes the converse for the two-files case. For more than two files, the upper bound is constructed by three successive channel transformations. Our results establish provable security guarantees against a powerful adversary which optimizes its tapping over both phases of communication in a cache-aided system.

cs.IT↗

arXiv2021

Energy-Harvesting Distributed Machine Learning

This paper provides a first study of utilizing energy harvesting for sustainable machine learning in distributed networks. We consider a distributed learning setup in which a machine learning model is trained over a large number of devices that can harvest energy from the ambient environment, and develop a practical learning framework with theoretical convergence guarantees. We demonstrate through numerical experiments that the proposed framework can significantly outperform energy-agnostic benchmarks. Our framework is scalable, requires only local estimation of the energy statistics, and can be applied to a wide range of distributed training settings, including machine learning in wireless networks, edge computing, and mobile internet of things.

cs.LG↗

arXiv2019

Learning an Adversary's Actions for Secret Communication

Secure communication over a wiretap channel is investigated, in which an active adversary modifies the state of the channel and the legitimate transmitter has the opportunity to sense and learn the adversary's actions. The adversary has the ability to switch the channel state and observe the corresponding output at every channel use while the encoder has causal access to observations that depend on the adversary's actions. A joint learning/transmission scheme is developed in which the legitimate users learn and adapt to the adversary's actions. For some channel models, it is shown that the achievable rates, defined precisely for the problem, are arbitrarily close to those obtained with hindsight, had the transmitter known the actions ahead of time. This initial study suggests that there is much to exploit and gain in physical-layer security by learning the adversary, e.g., monitoring the environment.

cs.IT↗

arXiv2019

QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning

The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks. To ensure robust communication against jamming, an interference-aware routing protocol is developed that allows nodes to avoid communication holes created by jamming attacks. Then, a distributed cooperation framework, based on deep reinforcement learning, is proposed that allows nodes to assess network conditions and make deep learning-driven, distributed, and real-time decisions on whether to participate in data communications, defend the network against jamming and eavesdropping attacks, or jam other transmissions. The objective is to maximize the network performance that incorporates throughput, energy efficiency, delay, and security metrics. Simulation results show that the proposed jamming-aware routing approach is robust against jamming and when throughput is prioritized, the proposed deep reinforcement learning approach can achieve significant (measured as three-fold) increase in throughput, compared to a benchmark policy with fixed roles assigned to nodes.

cs.NI↗

arXiv2019

Device-to-Device Secure Coded Caching

This paper studies device to device (D2D) coded-caching with information theoretic security guarantees. A broadcast network consisting of a server, which has a library of files, and end users equipped with cache memories, is considered. Information theoretic security guarantees for confidentiality are imposed upon the files. The server populates the end user caches, after which D2D communications enable the delivery of the requested files. Accordingly, we require that a user must not have access to files it did not request, i.e., secure caching. First, a centralized coded caching scheme is provided by jointly optimizing the cache placement and delivery policies. Next, a decentralized coded caching scheme is developed that does not require the knowledge of the number of active users during the caching phase. Both schemes utilize non-perfect secret sharing and one-time pad keying, to guarantee secure caching. Furthermore, the proposed schemes provide secure delivery as a side benefit, i.e., any external entity which overhears the transmitted signals during the delivery phase cannot obtain any information about the database files. The proposed schemes provide the achievable upper bound on the minimum delivery sum rate. Lower bounds on the required transmission sum rate are also derived using cut-set arguments indicating the multiplicative gap between the lower and upper bounds. Numerical results indicate that the gap vanishes with increasing memory size. Overall, the work demonstrates the effectiveness of D2D communications in cache-aided systems even when confidentiality constraints are imposed at the participating nodes and against external eavesdroppers.

cs.IT↗

arXiv2019

Secret-Key Generation in Many-to-One Networks: An Integrated Game-Theoretic and Information-Theoretic Approach

This paper considers secret-key generation between several agents and a base station that observe independent and identically distributed realizations of correlated random variables. Each agent wishes to generate the longest possible individual key with the base station by means of public communication. All keys must be jointly kept secret from all external entities. In this many-to-one secret-key generation setting, it can be shown that the agents can take advantage of a collective protocol to increase the sum-rate of their generated keys. However, when each agent is only interested in maximizing its own secret-key rate, agents may be unwilling to participate in a collective protocol. Furthermore, when such a collective protocol is employed, how to fairly allocate individual key rates arises as a valid issue. This paper studies this tension between cooperation and self-interest with a game-theoretic treatment. The work establishes that cooperation is in the best interest of all individualistic agents and that there exists individual secret-key rate allocations that incentivize the agents to follow the protocol. Additionally, an explicit coding scheme that achieves such allocations is proposed.

cs.IT↗

arXiv2019

Device-to-Device Coded Caching with Distinct Cache Sizes

This paper considers a cache-aided device-to-device (D2D) system where the users are equipped with cache memories of different size. During low traffic hours, a server places content in the users' cache memories, knowing that the files requested by the users during peak traffic hours will have to be delivered by D2D transmissions only. The worst-case D2D delivery load is minimized by jointly designing the uncoded cache placement and linear coded D2D delivery. Next, a novel lower bound on the D2D delivery load with uncoded placement is proposed and used in explicitly characterizing the minimum D2D delivery load (MD2DDL) with uncoded placement for several cases of interest. In particular, having characterized the MD2DDL for equal cache sizes, it is shown that the same delivery load can be achieved in the network with users of unequal cache sizes, provided that the smallest cache size is greater than a certain threshold. The MD2DDL is also characterized in the small cache size regime, the large cache size regime, and the three-user case. Comparisons of the server-based delivery load with the D2D delivery load are provided. Finally, connections and mathematical parallels between cache-aided D2D systems and coded distributed computing (CDC) systems are discussed.

cs.IT↗