With the rise of intelligent services on edge devices, the focus of intelligence formation has shifted to the user-side, enabling faster and customized services near the data source, without network overhead or privacy concerns. However, on-device edge intelligence faces some challenges caused by limited data availability and resource constraints in computation and memory. Fortunately, there is more and more intelligence nearby. To effectively harness the potential of widespread edge intelligence, we introduce CollectiveFL, a federated edge intelligence framework that facilitates de-biased, robust edge-to-edge knowledge transfer. By tailoring knowledge sharing for each device based on decision logic similarity, we ensure that edge-side learners specialize in their respective purposes and leverage purpose-specific data. Importantly, to mitigate some possible biases on their own or transferred local data, we delegate knowledge transfer to a set of selected neighboring devices rather than one. By sharing and consolidating collective yet customized intelligence, CollectiveFL establishes collaborative edge-only intelligence without the help of remote servers. Our extensive experimental results on four different model architectures using 13 public datasets have demonstrated that CollectiveFL enhances local learning in 55 out of 63 cases (87.3%) while improving the accuracy of individual tasks by up to 14.1%.

As wireless-equipped devices are widely deployed, fingerprint-based indoor localization becomes popular due to its simple yet precise feature. A key challenge is constructing an accurate map of signals with their corresponding coordinates. However, because the structural layout of each location uniquely affects signal propagation from distinct access points (APs), fingerprint maps cannot be transferred to other locations. This leads to localization failure in unexplored areas. In this paper, we propose CollageMap, an obstacle-aware fingerprint map constructor embracing generic signal features and AP-oriented unique features. We tackle the problem of fingerprint construction as a compound of two complementary maps: 1) obstacle-independent universal map reflecting intrinsic propagation patterns; and 2) obstacle-dependent adaptation map representing the extrinsic effect of obstacles. We construct a universal model that learns existing fingerprints in various training locations so that it can be generally used at any other place. On top of the universal map, another deep neural network (DNN) learns the real signal deviations between the universal map and the ground-truth map and generates the compensation as the adaptation map for obstructed environments. Using real-world received signal strength indicator (RSSI) testbeds across various wireless radios, we have validated CollageMap provides outstanding signal pattern estimation even in the presence of obstacles, achieving improvements in localization accuracy of up to 30.36%, 17.95%, and 16.97% using Wi-Fi, ZigBee, and BLE, respectively, via adaptation. CollageMap effectively keeps the performance gap of only 0.42%, 17.43 and 7.10% on average, compared to the ground-truth map obtained from the site survey.

The gradient attack problem has recently been studied to increase the awareness of people on privacy risks in federated learning. However, this attack is constrained under specific conditions, such as small image batch sizes and low image resolutions. To address this challenge, we introduce a new three-phase image recovery architecture called EncGradInversion, which harnesses the power of image encoding and the shared gradient inversion. In the first phase, we attempt to extract the representation for all of the images using the gradient at the final layer. Then, in the second phase, the extracted encoding of a specific image is leveraged for reconstructing the image by matching the representation of dummy and approximated images. This allows a parallel algorithm to accelerate the image recovery. In the final phase, the reconstructed images are fine tuned using the shared gradient of the whole network. In the second and third phases, we formulate an optimization problem to minimize the discrepancy between the shared and reconstructed gradients, while preserving the smoothness and natural appearance of the reconstructed images. Evaluated on various datasets and deep learning models, EncGradInversion shows its superiority to recover the original training images with resolutions as high as$1024\times 1024$and with the batch size of 512. Furthermore, the proposed architecture outperforms existing counterparts with a factor of up to 9.8 and 6.04, in terms of structural similarity performance and attack time.

Indoor localization using deep learning has emerged as a promising approach due to its high accuracy in mapping and predicting user locations for complex datasets. However, the inherent complexity of deep learning models often limits their interpretability, creating a gap in user trust and understanding. This paper introduces eXLoc, a novel framework that integrates Explainable AI, Class Activation Mapping (CAM), into deep learning models for indoor localization to enhance model transparency and interpretability. We introduce a new metric called Impact Score to identify significant APs that affect model predictions. This enhances model interpretability and allows a model to identify the influential APs via their impact on localization performance. We have extensively evaluated eXLoc over eight different places from two real-world RSSI datasets. We gained insights into how the model generates predictions, and identified the reasons for the model’s poor performance. These results demonstrate that our approach can be effectively utilized in enabling users to have more trust and understanding of the model in many real-world scenarios.

Deep learning models deployed on edge devices leverage locally collected data to extract intelligence, mitigating privacy concerns associated with external data sharing. Edge federated learning, an on-device learning paradigm, has emerged as a promising solution, allowing edge nodes to train models locally and share only the trained weights, preserving data privacy. However, it also poses critical challenges of network burden and potential model poisoning. We introduce a self-debiasing security framework Breakwater for multi-hop edge federated learning. We incorporate on-device malicious weight discriminator at each participant, enhancing security and robustness of the federated learning process. The framework strategically balances the benefits of participating nodes with timely defenses against potential malicious clients. Based on the discriminator, we further embed a self-debiasing mechanism that can determine whether to retain or discard the weight propagation from its child nodes. Our Breakwater framework identifies and filters out harmful weights, ensuring the integrity of the global model. Our work contributes to the ongoing discourse on federated learning security, presenting a solution that maintains efficiency while robustly defending against model poisoning threats. We demonstrate its efficacy in enhancing the reliability of the multi-hop edge federated learning process with recovery of up to 69 % in accuracy under attack, offering a path toward secure and cooperative distributed learning environments.

As indoor localization becomes a necessity to provide intelligent location-based services for in-building users, fingerprint-based positioning has been widely adopted in numerous Wi-Fi-equipped devices. However, its reliance on extensive offline site surveys limits its application in unexplored environments without prior fingerprint sampling. To address the challenge, we propose GAN-Loc, a novel generative fingerprint-based frame-work. We extract the underlying correlation between location and radio signal features, empowering indoor localization in un/under-explored areas, including unknown data points, newly deployed APs, or unexplored sites. It involves: 1) decomposing into a signal feature map for each AP perspective; 2) learning with a set of points and their associated signal strength data; 3) generating and integrating synthetic radio fingerprints; and 4) employing them into some existing localization algorithms. We evaluated GAN-Loc with extensive real-world RSSI measurements in seven different indoor places. GAN-Loc achieves the localization accuracy of up to 1.21m, 1.29m, and 1.28m for Wi-Fi, Zigbee, and BLE, respectively, compared to the accuracy of 1.47m, 1.58m, and 1.22m using an ideal ground-truth map, which is unachievable without site survey in unknown sites.

To reduce network intrusion detection latency in a high volume of data traffic, on-device detection with neuron pruning has been widely adopted by eliminating ineffective connections from a densely connected neural network. However, neuron pruning has a serious problem called output separation in which some parts of neurons can easily be pruned in the middle and become isolated from the rest of the network. To this end, we introduce a solution called the conservation of output links (COOL) pruning method that iteratively preserves a set of effective connections to avoid neuron isolation. We first evaluate COOL on MNIST and CIFAR-10 data sets as well as programmable networking devices, such as P4-supported switches. The experimental results show that COOL outperforms existing methods in terms of both detection time and classification accuracy, especially in extremely sparse networks. Compared to three representative pruning methods, our COOL-based classification model performs at least 25% more accurately with the upper bound for the pruning probability. To further display the effectiveness of COOL-based intrusion detection, we formulate a novel detection time minimization problem by assigning suitable detection models for switches in Internet of Things (IoT) under performance requirements and resource limitations. The experimental results demonstrate that our COOL algorithm is particularly useful for delay-critical and high-traffic applications.

In the era of artificial intelligence (AI), deep neural networks (DNNs) become larger using a massive amount of data, and thus, they are trained via cooperative computing devices (e.g., GPUs or servers) based on federated learning. As computation and data generation move to the edge due to privacy, latency, or bandwidth issue, DNN with edge devices has been investigated. However, edge devices are wirelessly connected and mostly incur fragile connectivity. We propose VersatileFL, a novel volatility-resilient deep learning framework under hostile environments. We address short-term and long-term volatility: 1) versatile distributed learning against short-term fluctuation by substituting the missing intermediate values with the past or approximated values and 2) model rearrangement with runtime connectivity diagnosis against long-term variation by adaptively adjusting the partitioned model for the impaired. We have demonstrated that VersatileFL has achieved 62.0% and 31.9% higher performance than hostile learning without a maintenance scheme against the short-term and long-term volatility, respectively.

Due to the outbreak of recent network attacks, it is necessary to develop a robust network intrusion detection system (NIDS) that can quickly and effectively identify the network attack. Although the state-of-the-art detection algorithms have shown quite promising detection performance, they suffer from computationally intensive operations and large memory footprint, making themselves infeasible to applications at the resourceconstrained edge devices. We propose a lightweight yet effective NIDS scheme that incorporates a stacked autoencoder with a network pruning technique. By removing a set of ineffective neurons across layers in the autoencoder network with a certain probability based on their importance, a considerably large portion of relatively nominal training parameters are reduced. Then, the pruned and pretrained encoder network is used as-is and is connected with a separate classifier network for attack type inference, avoiding a full retraining from scratch. Experimental results indicate that our stacked autoencoder-based classification network with probabilistic feature extraction has outperformed the state-of-the-art NIDSs in terms of attack detection rate. Further, we have shown that our lightweight NIDS scheme has significantly reduced the computational complexity throughout the architecture, making it feasible to the edge, while maintaining a similar attack type detection quality compared with its original fully connected neural network.

As intelligence recently moves to the edge to tackle the problems of privacy, scalability, and network bandwidth in the centralized intelligence, it is necessary to construct an efficient yet robust deep learning model viable at edge devices, which are usually volatile in wireless links and device functionality. The intensive computation burden for deep learning at the edge side necessitates some level of parallel processing via acceleration. We proposeEdgePipe, a deep learning framework based on deep neural networks (DNNs) with a mixture of model parallelism and pipeline training for high resource utilization over volatile wireless edge devices. To tackle the volatility problem in wireless links and device functionality, a concept ofsuper neuronis defined to be a group of neurons across adjacent layers, which is the basis of model partitioning at edge devices. The relatively loss-resilient neuron structure prevents the entire forward or backward training paths from being totally broken down due to only some intermittent link or device failure caused by one or few devices. Furthermore, we design a subsequent pipeline training mechanism based on the prior super-neuron-based model partitioning for fast convergence with more training data in a fixed timeline. The experimental results have demonstrated thatEdgePipeoutperforms several counterpart algorithms includingPipeDreamunder the volatile wireless lossy or device malfunctioning environments, while preserving the low interlayer communication overhead.

In the era of edge computing and Artificial Intelligence (AI), securing billions of edge devices within a network against intelligent attacks is crucial. We propose PUFGAN, an innovative machine learning attack-proof security architecture, by embedding a self-adversarial agent within a device fingerprint- based security primitive, public PUF (PPUF) known for its strong fingerprint-driven cryptography. The self-adversarial agent is implemented using Generative Adversarial Networks (GANs). The agent attempts to self-attack the system based on two GAN variants, vanilla GAN and conditional GAN. By turning the attacking quality through generating realistic secret keys used in the PPUF primitive into system vulnerability, the security architecture is able to monitor its internal vulnerability. If the vulnerability level reaches at a specific value, PUFGAN allows the system to restructure its underlying security primitive via feedback to the PPUF hardware, maintaining security entropy at as high a level as possible. We evaluated PUFGAN on three different machine environments: Google Colab, a desktop PC, and a Raspberry Pi 2, using a real-world PPUF dataset. Extensive experiments demonstrated that even a strong device fingerprint security primitive can become vulnerable, necessitating active restructuring of the current primitive, making the system resilient against extreme attacking environments.

In this paper, we consider an aerial ad-hoc network construction problem using UAVs in a disaster scenario. We aim to reconnect the communication-wise isolated urban area with the outside communication infrastructure. Our main goal is to perform both network exploration and relay deployment tasks at the same time by taking a progressive optimization toward a self-organizing network construction. We propose a novel UAV exploration-and-deployment algorithm that gradually explores the region of interests and achieves full network coverage in a fast manner. Then, we present an effective network refinement algorithm based on clustering that minimizes the number of UAVs for deployment by finding out essential UAVs, while keeping the similar network coverage performance. Simulation results demonstrate that our proposed scheme significantly reduces the execution time for network exploration and deployment compared to a baseline counterpart. Also, our cluster-based network refinement algorithm provides a very lightweight yet effective solution, well-balancing between UAV resource and computation overhead.

We consider a 3D network construction problem in the post-disaster scenario, where large urban areas are communication-wise isolated from the outside environment due to the severely damaged network infrastructure. Our main goal is to reconnect the isolated regions with the outside environment using unmanned aerial vehicles (UAVs) by building 3D aerial ad-hoc networks. Prior to network construction, we aim to capture the global map information over region of interests (RoI) by exploring all obstacles in the unknown region. We propose an efficient technique for collaborative 3D terrestrial exploration using multiple UAVs based on our distributed path planning algorithm, which finds collision-free exploration paths. Then, we present an optimal full-coverage 3D aerial ad-hoc network construction by deploying the minimum number of UAVs to indispensable spots while obtaining maximum network coverage. Simulation results demonstrate that our proposed exploration scheme outperforms several counterpart algorithms in terms of traversal time and redundant visit rate. Also, our network construction algorithm guarantees almost full coverage toward terrestrial space with only minimal UAV usage.

In this paper, we address a route reconstruction problem using Unmanned Aerial Vehicles (UAVs) after a large-scale disaster where stationary ad-hoc networks are severely destructed. The main goal of this paper is to improve routing performance in a progressive manner by reconnecting partitioned networks through dispatched UAV relays. Our proposed algorithm uses two types of UAVs: global and local UAVs to collaboratively find the best deployment position in a dynamically changing environment. To obtain terrestrial network connectivity information and extract high-level network topology, we exploit the concept of strongly connected component in graph theory. Based on the understanding from a global point view, global UAVs recommend the most effective deployment positions to local UAVs so that they are deployed as relays in more critically disrupted areas. Simulation-based experiments validate that our distributed route reconstruction algorithm outperforms a counterpart algorithm in terms of steady-state and dynamic routing performance.

In this paper, we consider a route recovery problem using Unmanned Aerial Vehicles (UAVs) as relay nodes to connect with terrestrial ad-hoc networks in realistic disaster scenarios. Our main goal is to perform network probing from the air by UAVs and find out crucial spots where both local and global routing performance can significantly be recovered if they are deployed. We propose a route topology discovery scheme that extracts the inherent route skeletons by stitching partial local paths obtained from simple packet probing by UAVs, while exploring a designated Region of Interest (RoI) by an adaptive traversing scheme. By leveraging the captured topology, we dispatch a limited number of UAVs by an iterative UAV deployment algorithm and provide a lightweight yet effective network hole replacement decision in a heuristic manner. Simulation results demonstrate that our traversing algorithm reduces the complete coverage time, the travel distance, and the duplicate coverage compared to a previous work, DroneNet. Our subsequent iterative deployment algorithm greatly recovers severely impaired routes in a damaged network, while substantially reducing computational complexity.

A low-end embedded platform for Internet of Things (IoT) often suffers from a critical trade-off dilemma between security enhancement and computation overhead. We propose PUFSec, a new device fingerprint-based security architecture for IoT devices. By leveraging intrinsic hardware characteristics, we aim to design a computationally lightweight security software system architecture so that complex cryptography computation can dramatically be prohibited. We exploit the innovative idea of Public Physical Unclonable Functions (PPUFs) that fundamentally protects attackers from recovering the secret key from public gate delay information. We implement its hardware logic in a real-world FPGA board. On top of the PPUF fingerprint hardware, we present an adaptive security control mechanism consisting of adaptive key generation and key exchange protocol, which adjusts security strength depending on system load dynamics. We demonstrate that our PPUF FPGA implementation embeds distinctive variability enough to distinguish between two different PPUFs with high fidelity. We validate our PUFSec architecture by implementing necessary algorithms and protocols in a real-world IoT platform, and performing empirical evaluation in terms of computation and memory usages, proving its practical feasibility.

We consider the problem of path planning using multiple UAVs as message ferries to deliver delay-sensitive information in a catastrophic disaster scenario. Our main goal is to find the optimal paths of UAVs to maximize the number of nodes that can successfully be serviced within each designated packet deadline. At the same time, we want to reduce total travel time for visiting over a virtual grid topology. We propose a distributed path planning algorithm that determines the next visit grid point based on a weighted sum of travel time and delivery deadline. Together with path planning, we incorporate a task division mechanism that collaboratively distributes the unvisited grid points with other UAVs so that the entire travel time can substantially be reduced. Simulation results demonstrate that our distributed path planning algorithm mixed with task division outperforms all baseline counterpart algorithms in terms of on-time service node rate and total travel time.

In this paper, we consider the problem of distributing patrol officers inside a building to maximize the probability of catching multiple intruders while minimizing the distance the patrol officers travel to reach the locations of the intruders. In our problem setting, the patrol officers are assisted by the information collected by a network of binary proximity sensors installed in the building. We claim that learning even common movement sub-patterns that originate due to the constrained physical environment helps to find likely locations of intruders where each major location is instrumented using a sensor node. We use a series of binary detection events to infer likely future trajectories in a real-world building. For a given set of detectable nodes on the inferred future trajectories, we aim to find the optimal patrol dispatch node location with high exposure to intruders' future appearance using patrol officers in limited numbers, ideally fewer than the intruders. In order to prevent possible crime and perform responsive defense against potential intruders, our algorithm also tries to reduce the travel distance from patrols current positions to their dispatched positions at the same time. We validate our proposed scheme in terms of detection accuracy by varying the number of intruders, robustness against missing events, and responsiveness compared to a practical baseline counterpart through real-world system experiments.

We present a social-aware data forwarding scheme from a mobile source to a mobile destination in disruption tolerant networks. By incorporating any scattered network devices as temporal data storage for forwarding into parts of forwarding path, we aim to find the most effective relay path consisting of mobile-to-stationary and stationary-to-mobile relays. We combine the “carry-and-forward” scheme for stationary-to-mobile transmission with the “store-and-forward” for mobile-to-stationary transmission for improving both delivery rate and packet delay performance. We formulate this relay selection problem into a mixed-integer linear program, considering two crucial QoS constraints of packet delivery rate and deadline. We find the optimal forwarding path of all relevant mobile relays as well as their corresponding stationary nodes as bridges between mobile relays. We validate our algorithm based on a real-world dataset in terms of routing cost and packet transmission time compared to a baseline counterpart.

In this paper, we consider a network reconstruction problem using UAVs where stationary ad-hoc networks are severely damaged in a post-disaster scenario. The main objective of this paper is to repair network by supplementing aerial wireless links into the stationary network to reconnect isolated ground networks each other with a limited number of UAVs. We propose a distributed motion planning that guarantees complete coverage to probe network connectivity from the air over stationary networks, while reducing duplicate coverage with other UAVs. Given the collected local connectivity information over region of interest, we deploy UAVs as relays into the locations of network holes to repair network-wide data delivery most effectively by formulating the problem into a binary integer program. Simulation results show that our network traversing algorithm outperforms a multi-agent exploration algorithm Ants in terms of complete coverage time, travel distance, and duplicate coverage. Also, our deployment optimization enhances network-wide routing performance compared to a practical baseline counterpart.

In this paper, we present a routing scheme that exploits knowledge about the behavior of mobile sinks within a network of data sources to minimize energy consumption and network congestion. For delay-tolerant network applications, we propose to route data not to the sink directly, but to send it instead to a relay node along an announced or predicted path of the mobile node that is close to the data source. The relay node will stash the information until the mobile node passes by and picks up the data. We use linear programming to find optimal relay nodes that minimize the number of necessary transmissions while guaranteeing robustness against link and node failures, as well as trajectory uncertainty.

This paper presents a cooperative relay strategy with a game-theoretic perspective. In multi-hop networks, each node needs to send traffic via relay nodes, which behave independently while staying aware of energy constraints. To encourage a relay to forward the packets, the proposed scheme formulates a Stackelberg game where two nodes sequentially bid their willingness weights to cooperate for their own benefits. Accordingly, all the nodes are encouraged to be cooperative only if a sender is cooperative and alternatively to be non-cooperative only if a sender is non-cooperative. This selective strategy changes the reputations of nodes depending on the amount of their bidding at each game and motivates them to maintain a good reputation so that all their respective packets can be treated well by other relays. This paper analyzes a Nash equilibrium from the proposed scheme and validates a sequential-move game by Stackelberg competition as opposed to a simultaneous-move game by Cournot competition. Simulation results demonstrate that the proposed scheme turns non-cooperative nodes into cooperative nodes and increases the cooperative relaying stimulus all over the nodes. Thus, every node forwards other packets with higher probability, thereby achieving a higher overall payoff.

We propose an interference-aware MAC protocol using a simple transmission strategy motivated by a game- theoretic approach. We formulate a channel access game, which considers nodes concurrently transmitting in nearby clusters, incorporating a realistic wireless communication model - the SINR model. Under inter-cluster interference, we derive a decentralized transmission strategy, which achieves a Bayesian Nash Equilibrium (BNE). The proposed MAC protocol balances network throughput and battery consumption at each transmission. We compare our BNE-based decentralized strategy with a centralized globally optimal strategy in terms of efficiency and balance. We further show that the transmission threshold should be adaptively tuned depending on the number of active users in the network, crosstalk, ambient noise, transmission cost, and radio-dependent receiver sensitivity. We also present a simple dynamic procedure for nodes to efficiently find a Nash Equilibrium (NE) without requiring each node to know the total number of active nodes or the channel gain distribution, and prove that this procedure is guaranteed to converge.

We propose modeling environmental noise in order to efficiently and accurately simulate wireless packet delivery. We measure noise traces in many different environments and propose three algorithms to simulate noise from these traces. We evaluate applying these algorithms to signal-to-noise curves in comparison to existing simulation approaches used in EmStar, TOSSIM, and ns2. We measure simulation accuracy using the Kantorovich-Wasserstein distance on conditional packet delivery functions. We demonstrate that using a closest-fit pattern matching (CPM) noise model can capture complex temporal dynamics which existing approaches do not, increasing packet simulation fidelity by a factor of 2 for good links, a factor of 1.5 for bad links, and a factor of 5 for intermediate links. As our models are derived from real-world traces, they can be generated for many different environments.