arXiv subjects

Yi Shi

Publications and source records attributed to Yi Shi.

At least 127 records · Page 7Linked to original sources

arXiv2020

Deep Learning for Wireless Communications

Existing communication systems exhibit inherent limitations in translating theory to practice when handling the complexity of optimization for emerging wireless applications with high degrees of freedom. Deep learning has a strong potential to overcome this challenge via data-driven solutions and improve the performance of wireless systems in utilizing limited spectrum resources. In this chapter, we first describe how deep learning is used to design an end-to-end communication system using autoencoders. This flexible design effectively captures channel impairments and optimizes transmitter and receiver operations jointly in single-antenna, multiple-antenna, and multiuser communications. Next, we present the benefits of deep learning in spectrum situation awareness ranging from channel modeling and estimation to signal detection and classification tasks. Deep learning improves the performance when the model-based methods fail. Finally, we discuss how deep learning applies to wireless communication security. In this context, adversarial machine learning provides novel means to launch and defend against wireless attacks. These applications demonstrate the power of deep learning in providing novel means to design, optimize, adapt, and secure wireless communications.

cs.NI↗

arXiv2020

When Wireless Security Meets Machine Learning: Motivation, Challenges, and Research Directions

Wireless systems are vulnerable to various attacks such as jamming and eavesdropping due to the shared and broadcast nature of wireless medium. To support both attack and defense strategies, machine learning (ML) provides automated means to learn from and adapt to wireless communication characteristics that are hard to capture by hand-crafted features and models. This article discusses motivation, background, and scope of research efforts that bridge ML and wireless security. Motivated by research directions surveyed in the context of ML for wireless security, ML-based attack and defense solutions and emerging adversarial ML techniques in the wireless domain are identified along with a roadmap to foster research efforts in bridging ML and wireless security.

cs.NI↗

arXiv2019

Coherent Communications in Self-Organizing Networks with Distributed Beamforming

Coherent communications aim to support higher data rates and extended connectivity at lower power consumption compared with traditional point-to-point transmissions. The typical setting of coherent communication schemes is based on a single data stream with multiple transmitters and a single receiver. This paper studies the case of multiple concurrent data streams, each with multiple transmitters and multiple receivers, in self-organizing wireless networks. A distributed optimization solution based on joint network formation and beamforming is developed for coherent group communications in a network of nodes that need to communicate over long distances. This solution significantly improves the power gain for a single data stream and the signal-to-interference-ratio for multiple data streams compared to point-to-point communications. These gains are in turn translated to improvements in communication range, power efficiency, reliability, and throughput. In this multi-layer network optimization solution, nodes coordinate with each other in a distributed manner to form transmitter and receiver groups, and communicate with each other coherently over long distances. The coherent beamforming protocol is optimized for given transmitter and receiver groups, whereas the network formation protocol is optimized to determine these groups. By using single-antenna communication nodes, the proposed optimization solution provides a major gain in network communications and outperforms other benchmark combinations of beamforming and network formation protocols.

cs.NI↗

arXiv2019

Cross-layer Design and SDR Implementation of DSA, Backpressure Routing and Network Coding

A cross-layer cognitive radio system is designed to support unicast and multicast traffic with integration of dynamic spectrum access (DSA), backpressure algorithm, and network coding for multi-hop networking. The full protocol stack that operates with distributed coordination and local information exchange is implemented with software-defined radios (SDRs) and assessed in a realistic test and evaluation (T\&E) system based on a network emulation testbed. Without a common control channel, each SDR performs neighborhood discovery, spectrum sensing and channel estimation, and executes a distributed extension of backpressure algorithm that optimizes the spectrum utility (that represents link rates and traffic congestion) with joint DSA and routing. The backpressure algorithm is extended to support multicast traffic with network coding deployed over virtual queues (for multicast destinations). In addition to full rank decoding at destinations, rank deficient decoding is also considered to reduce the delay. Cognitive network functionalities are programmed with GNU Radio and Python modules are developed for different layers. USRP radios are used as RF front ends. A wireless network T\&E system is presented to execute emulation tests, where radios communicate with each other through a wireless network emulator that controls physical channels according to path loss, fading, and topology effects. Emulation tests are presented for different topologies to evaluate the throughput, backlog and energy consumption. Results verify the SDR implementation and the joint effect of DSA, backpressure routing and network coding under realistic channel and radio hardware effects.

cs.NI↗

arXiv2019

Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks

An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks. A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission. In the meantime, an adversary learns the transmitter's behavior (exploratory attack) by building another deep neural network to predict when transmissions will succeed. The adversary falsifies (poisons) the transmitter's spectrum sensing data over the air by transmitting during the short spectrum sensing period of the transmitter. Depending on whether the transmitter uses the sensing results as test data to make transmit decisions or as training data to retrain its deep neural network, either it is fooled into making incorrect decisions (evasion attack), or the transmitter's algorithm is retrained incorrectly for future decisions (causative attack). Both attacks are energy efficient and hard to detect (stealth) compared to jamming the long data transmission period, and substantially reduce the throughput. A dynamic defense is designed for the transmitter that deliberately makes a small number of incorrect transmissions (selected by the confidence score on channel classification) to manipulate the adversary's training data. This defense effectively fools the adversary (if any) and helps the transmitter sustain its throughput with or without an adversary present.

cs.NI↗

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

Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments

Dynamic spectrum access (DSA) benefits from detection and classification of interference sources including in-network users, out-network users, and jammers that may all coexist in a wireless network. We present a deep learning based signal (modulation) classification solution in a realistic wireless network setting, where 1) signal types may change over time; 2) some signal types may be unknown for which there is no training data; 3) signals may be spoofed such as the smart jammers replaying other signal types; and 4) different signal types may be superimposed due to the interference from concurrent transmissions. For case 1, we apply continual learning and train a Convolutional Neural Network (CNN) using an Elastic Weight Consolidation (EWC) based loss. For case 2, we detect unknown signals via outlier detection applied to the outputs of convolutional layers using Minimum Covariance Determinant (MCD) and k-means clustering methods. For case 3, we extend the CNN structure to capture phase shifts due to radio hardware effects to identify the spoofing signal sources. For case 4, we apply blind source separation using Independent Component Analysis (ICA) to separate interfering signals. We utilize the signal classification results in a distributed scheduling protocol, where in-network (secondary) users employ signal classification scores to make channel access decisions and share the spectrum with each other while avoiding interference with out-network (primary) users and jammers. Compared with benchmark TDMA-based schemes, we show that distributed scheduling constructed upon signal classification results provides major improvements to in-network user throughput and out-network user success ratio.

cs.NI↗

arXiv2019

Integrating high-quality dielectrics with one-nanometer equivalent oxide thickness on two-dimensional electronic devices

Two-dimensional (2D) semiconductors are widely recognized as attractive channel materials for low-power electronics. However, an unresolved challenge is the integration of high-quality, ultrathin high-\k{appa} dielectrics that fully meet the roadmap requirements for low-power applications. With a dangling-bond free surface, the deposition of dielectrics by atomic layer deposition (ALD) on 2D materials is usually characterized with non-uniform nucleation and island formation, producing a highly porous dielectric layer with serious leakage particularly at the small equivalent oxide thickness (EOT) limit. Here, we report the robust ALD of highly uniform high-\k{appa} dielectric on 2D semiconductors by using ~0.3 nm-thick exclusively monolayer molecular crystal as seeding layer. Ultrathin dielectrics down to 1 nm EOT is realized on graphene, MoS2 and WSe2, with considerably reduced roughness, density of interface states, leakage current and improved breakdown field compared to prior methods. Taking advantage of the reduced EOT, we demonstrate graphene RF transistors operating at 60 GHz, as well as MoS2 and WSe2 complementary metal-oxide-semiconductor (CMOS) transistors with Vdd =0.8 V and ideal subthreshold swing (SS) of 60 mV/dec, 20 nm-channel-length MoS2 transistors with on/off ratio over 10^7. These studies highlight that our dielectric integration method is generally applicable for different 2D materials, and compatible with top-down fabrication process on large-area chemical vapor deposited films.

physics.app-ph↗

arXiv2019

A countable partition for singular flows, and its application on the entropy theory

In this paper, we construct a countable partition $\mathscr{A}$ for flows with hyperbolic singularities by introducing a new cross section at each singularity. Such partition forms a Kakutani tower in a neighborhood of the singularity, and turns out to have finite metric entropy for every invariant probability measure. Moreover, each element of $\mathscr{A}^\infty$ will stay in a scaled tubular neighborhood for arbitrarily long time. This new construction enables us to study entropy theory for singular flows away from homoclinic tangencies, and show that the entropy function is upper semi-continuous with respect to both invariant measures and the flows.

math.DS↗

arXiv2019

IoT Network Security from the Perspective of Adversarial Deep Learning

Machine learning finds rich applications in Internet of Things (IoT) networks such as information retrieval, traffic management, spectrum sensing, and signal authentication. While there is a surge of interest to understand the security issues of machine learning, their implications have not been understood yet for wireless applications such as those in IoT systems that are susceptible to various attacks due the open and broadcast nature of wireless communications. To support IoT systems with heterogeneous devices of different priorities, we present new techniques built upon adversarial machine learning and apply them to three types of over-the-air (OTA) wireless attacks, namely jamming, spectrum poisoning, and priority violation attacks. By observing the spectrum, the adversary starts with an exploratory attack to infer the channel access algorithm of an IoT transmitter by building a deep neural network classifier that predicts the transmission outcomes. Based on these prediction results, the wireless attack continues to either jam data transmissions or manipulate sensing results over the air (by transmitting during the sensing phase) to fool the transmitter into making wrong transmit decisions in the test phase (corresponding to an evasion attack). When the IoT transmitter collects sensing results as training data to retrain its channel access algorithm, the adversary launches a causative attack to manipulate the input data to the transmitter over the air. We show that these attacks with different levels of energy consumption and stealthiness lead to significant loss in throughput and success ratio in wireless communications for IoT systems. Then we introduce a defense mechanism that systematically increases the uncertainty of the adversary at the inference stage and improves the performance. Results provide new insights on how to attack and defend IoT networks using deep learning.

cs.NI↗

arXiv2019

Rigidity of center Lyapunov exponents and $su$-integrability

Let $f$ be a conservative partially hyperbolic diffeomorphism, which is homotopic to an Anosov automorphism $A$ on $\mathbb{T}^3$. We show that the stable and unstable bundles of $f$ are jointly integrable if and only if every periodic point of $f$ admits the same center Lyapunov exponent with $A$. In particular, $f$ is Anosov. Thus every conservative partially hyperbolic diffeomorphism, which is homotopic to an Anosov automorphism on $\mathbb{T}^3$, is ergodic. This proves the Ergodic Conjecture proposed by Hertz-Hertz-Ures on $\mathbb{T}^3$.

math.DS↗

arXiv2019

Generative Adversarial Network for Wireless Signal Spoofing

The paper presents a novel approach of spoofing wireless signals by using a general adversarial network (GAN) to generate and transmit synthetic signals that cannot be reliably distinguished from intended signals. It is of paramount importance to authenticate wireless signals at the PHY layer before they proceed through the receiver chain. For that purpose, various waveform, channel, and radio hardware features that are inherent to original wireless signals need to be captured. In the meantime, adversaries become sophisticated with the cognitive radio capability to record, analyze, and manipulate signals before spoofing. Building upon deep learning techniques, this paper introduces a spoofing attack by an adversary pair of a transmitter and a receiver that assume the generator and discriminator roles in the GAN and play a minimax game to generate the best spoofing signals that aim to fool the best trained defense mechanism. The output of this approach is two-fold. From the attacker point of view, a deep learning-based spoofing mechanism is trained to potentially fool a defense mechanism such as RF fingerprinting. From the defender point of view, a deep learning-based defense mechanism is trained against potential spoofing attacks when an adversary pair of a transmitter and a receiver cooperates. The probability that the spoofing signal is misclassified as the intended signal is measured for random signal, replay, and GAN-based spoofing attacks. Results show that the GAN-based spoofing attack provides a major increase in the success probability of wireless signal spoofing even when a deep learning classifier is used as the defense.

eess.SP↗

arXiv2019

Observation of ballistic avalanche phenomena in nanoscale vertical InSe/BP heterostructures

Initiating impact ionization of avalanche breakdown essentially requires applying a high electric field in a long active region, hampering carrier-multiplication with high gain, low bias and superior noise performance. Here we report the observation of ballistic avalanche phenomena in sub-MFP scaled vertical indium selenide (InSe)/black phosphorus (BP) heterostructures. The heterojunction is engineered to avalanche photodetectors (APD) and impact ionization transistors, demonstrating ultra-sensitive mid-IR light detection (4 μm wavelength) and ultra-steep subthreshold swing, respectively. These devices show an extremely low avalanche threshold (<1 volt), excellent low noise figures and distinctive density spectral shape. Further transport measurement evidences the breakdown originals from a ballistic avalanche phenomenon, where the sub-MFP BP channel enables both electrons and holes to impact-ionize the lattice and abruptly amplify the current without scattering from the obstacles in a deterministic nature. Our results shed light on the development of advanced photodetectors and efficiently facilitating carriers on the nanoscale.

cond-mat.mtrl-sci↗

arXiv2019

Spectrum Data Poisoning with Adversarial Deep Learning

Machine learning has been widely applied in wireless communications. However, the security aspects of machine learning in wireless applications have not been well understood yet. We consider the case that a cognitive transmitter senses the spectrum and transmits on idle channels determined by a machine learning algorithm. We present an adversarial machine learning approach to launch a spectrum data poisoning attack by inferring the transmitter's behavior and attempting to falsify the spectrum sensing data over the air. For that purpose, the adversary transmits for a short period of time when the channel is idle to manipulate the input for the decision mechanism of the transmitter. The cognitive engine at the transmitter is a deep neural network model that predicts idle channels with minimum sensing error for data transmissions. The transmitter collects spectrum sensing data and uses it as the input to its machine learning algorithm. In the meantime, the adversary builds a cognitive engine using another deep neural network model to predict when the transmitter will have a successful transmission based on its spectrum sensing data. The adversary then performs the over-the-air spectrum data poisoning attack, which aims to change the channel occupancy status from idle to busy when the transmitter is sensing, so that the transmitter is fooled into making incorrect transmit decisions. This attack is more energy efficient and harder to detect compared to jamming of data transmissions. We show that this attack is very effective and reduces the throughput of the transmitter substantially.

cs.NI↗

arXiv2019

Generative Adversarial Networks for Black-Box API Attacks with Limited Training Data

As online systems based on machine learning are offered to public or paid subscribers via application programming interfaces (APIs), they become vulnerable to frequent exploits and attacks. This paper studies adversarial machine learning in the practical case when there are rate limitations on API calls. The adversary launches an exploratory (inference) attack by querying the API of an online machine learning system (in particular, a classifier) with input data samples, collecting returned labels to build up the training data, and training an adversarial classifier that is functionally equivalent and statistically close to the target classifier. The exploratory attack with limited training data is shown to fail to reliably infer the target classifier of a real text classifier API that is available online to the public. In return, a generative adversarial network (GAN) based on deep learning is built to generate synthetic training data from a limited number of real training data samples, thereby extending the training data and improving the performance of the inferred classifier. The exploratory attack provides the basis to launch the causative attack (that aims to poison the training process) and evasion attack (that aims to fool the classifier into making wrong decisions) by selecting training and test data samples, respectively, based on the confidence scores obtained from the inferred classifier. These stealth attacks with small footprint (using a small number of API calls) make adversarial machine learning practical under the realistic case with limited training data available to the adversary.

cs.LG↗

arXiv2018

Deep Learning for Launching and Mitigating Wireless Jamming Attacks

An adversarial machine learning approach is introduced to launch jamming attacks on wireless communications and a defense strategy is presented. A cognitive transmitter uses a pre-trained classifier to predict the current channel status based on recent sensing results and decides whether to transmit or not, whereas a jammer collects channel status and ACKs to build a deep learning classifier that reliably predicts the next successful transmissions and effectively jams them. This jamming approach is shown to reduce the transmitter's performance much more severely compared with random or sensing-based jamming. The deep learning classification scores are used by the jammer for power control subject to an average power constraint. Next, a generative adversarial network (GAN) is developed for the jammer to reduce the time to collect the training dataset by augmenting it with synthetic samples. As a defense scheme, the transmitter deliberately takes a small number of wrong actions in spectrum access (in form of a causative attack against the jammer) and therefore prevents the jammer from building a reliable classifier. The transmitter systematically selects when to take wrong actions and adapts the level of defense to mislead the jammer into making prediction errors and consequently increase its throughput.

cs.NI↗

arXiv2018

Ultrafast photocarrier recombination dynamics in black phosphorus-molybdenum disulfide (BP/MoS2) heterostructure

Van der Waals (vdW) heterostructures constructed with two-dimensional (2D) materials have attracted great interests, due to their fascinating properties and potential for novel applications. While earlier efforts have advanced the understanding of the ultrafast cross-layer charge transfer process in 2D heterostructures, mechanisms for the interfacial photocarrier recombination remain, to a large extent, unclear. Here, we investigate a heterostructure comprised of black phosphorus (BP) and molybdenum disulfide (MoS2), with a type-II band alignment. Interestingly, it is found that the photo-generated electrons in MoS2 (transferred from BP) exhibit an ultrafast lifetime of about 5 ps, significantly shorter than those of the constituent materials. By corroborating with the relaxation of photo-excited holes in BP, it is revealed that the ultrafast time constant is as a result of efficient Langevin recombination, where the high hole mobility of BP facilitates a large recombination coefficient (approximately 2x10^-10 m^2/s). In addition, broadband transient absorption spectroscopy confirms that the hot electrons transferred to MoS2 distribute over a broad energy range following an ultrafast thermalization. The rate of the interlayer Langevin recombination is found to exhibit no energy level dependence. Our findings provide essential insights into the fundamental photo-physics in type-II 2D heterostructures, and also provide useful guidelines for customizing photocarrier lifetimes of BP for high-speed photo-sensitive devices.

cond-mat.mes-hall↗

arXiv2018

Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls

Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial machine learning in the form of back-box attacks on online classifier APIs. We start with a deep learning based exploratory (inference) attack, which aims to build a classifier that can provide similar classification results (labels) as the target classifier. To minimize the difference between the labels returned by the inferred classifier and the target classifier, we show that the deep learning based exploratory attack requires a large number of labeled training data samples. These labels can be collected by calling the online API, but usually there is some strict rate limitation on the number of allowed API calls. To mitigate the impact of limited training data, we develop an active learning approach that first builds a classifier based on a small number of API calls and uses this classifier to select samples to further collect their labels. Then, a new classifier is built using more training data samples. This updating process can be repeated multiple times. We show that this active learning approach can build an adversarial classifier with a small statistical difference from the target classifier using only a limited number of training data samples. We further consider evasion and causative (poisoning) attacks based on the inferred classifier that is built by the exploratory attack. Evasion attack determines samples that the target classifier is likely to misclassify, whereas causative attack provides erroneous training data samples to reduce the reliability of the re-trained classifier. The success of these attacks show that adversarial machine learning emerges as a feasible threat in the realistic case with limited training data.

cs.LG↗