While biometric-face and whole-body-recognition technology have recently advanced and matured, there are increasing interests in enhanced long-range recognition capabilities. However, long-range recognition requires the use of large, specialized datasets to support research and development for next generation systems. Moreover, existing datasets are further limited by the types of modalities (face or whole-body), number of subjects, maximum standoff distance, clothing variability, or availability restrictions. For long-range recognition, low-quality probe (query) images, which are often acquired from extended standoff distances or aerial platforms, are matched against higher quality gallery images and frequently results in poor identification performance. To address the growing needs for relevant data sources, a large-scale biometric dataset was collected and curated for long-range biometric recognition. This dataset is comprised of more than 1.2 million outdoor and 250,000 indoor (face and whole-body) images from more than 250 subjects that were acquired using various high-end cameras, including Canon and Nikon DSLR cameras, surveillance cameras, specialized long-range face cameras, and UAV platforms. The primary goal of this dataset is to support the development of algorithms for face and whole-body recognition at extended standoff distances. The availability of such a dataset is crucial in advancing technology for recognition under challenging conditions such as atmospheric turbulence.

Distributed surveillance systems have the ability to detect, track, and snapshot objects moving around in a certain space. The systems generate video data from multiple personal devices or street cameras. Intelligent video-analysis models are needed to learn dynamic representation of the objects for detection and tracking. Can we exploit the structural and dynamic information without storing the spatiotemporal video data at a central server that leads to a violation of user privacy? In this work, we introduce Federated Dynamic Graph Neural Network (Feddy), a distributed and secured framework to learn the object representations from graph sequences: (1) It aggregates structural information from nearby objects in the current graph as well as dynamic information from those in the previous graph. It uses a self-supervised loss of predicting the trajectories of objects. (2) It is trained in a federated learning manner. The centrally located server sends the model to user devices. Local models on the respective user devices learn and periodically send their learning to the central server without ever exposing the user’s data to server. (3) Studies showed that the aggregated parameters could be inspected though decrypted when broadcast to clients for model synchronizing, after the server performed a weighted average. We design an appropriate aggregation mechanism of secure aggregation primitives that can protect the security and privacy in federated learning with scalability. Experiments on four video camera datasets as well as simulation demonstrate that Feddy achieves great effectiveness and security.

Histograms have a large variety of useful applications in data analysis, e.g., tracking the spread of diseases and analyzing public health issues. However, most data analysis techniques used in practice operate over plaintext data, putting the privacy of users’ data at risk. We consider the problem of allowing an untrusted aggregator to privately compute a histogram over multiple users’ private inputs (e.g., number of contacts at a place) without learning anything other than the final histogram. This is a challenging problem to solve when the aggregators and the users may be malicious and collude with each other to infer others’ private inputs, as existing black box techniques incur high communication and computational overhead that limit scalability. We address these concerns by building a novel, efficient, and scalable protocol that intelligently combines a Trusted Execution Environment (TEE) and the Durstenfeld-Knuth uniformly random shuffling algorithm to update a mapping between buckets and keys by using a deterministic cryptographically secure pseudorandom number generator. In addition to being provably secure, experimental evaluations of our technique indicate that it generally outperforms existing work by several orders of magnitude, and can achieve performance that is within one order of magnitude of protocols operating over plaintexts that do not offer any security.

In this paper, we discuss a tensor decomposition method for imputing similarity scores between individual clinical pictures at predefined patient age intervals in order to construct a dynamic similarity network of patients with respect to early childhood anthropomorphic development. The method leverages Canonical Polyadic Decomposition (or PARAFAC) to compute missing Euclidean similarity scores between pairwise growth pictures, made up of height and weight measurements. We construct a tensor made up of serial affinity matrices to model how the similarities between different patients change over different trajectory snapshots. We intend to use this method to aid Un Kilo de Ayuda (UKA), a non-governmental organization located in Mexico that is made up of facilitators seeking to identify children at risk for malnutrition and suboptimal development. This tensor completion strategy will assist UKA with determining pairs of children with similar clinical pictures, so that they can better assist with selecting treatment strategies and ultimately build better programs tailored to specific families' needs.

Cloud computing is often utilized for file storage. Clients of cloud storage services want to ensure the privacy of their data, and both clients and servers want to use as little storage as possible. Cross-user deduplication is one method to reduce the amount of storage a server uses. Deduplication and privacy are naturally conflicting goals, especially for nearly-identical ("fuzzy") deduplication, as some information about the data must be used to perform deduplication. Prior solutions thus utilize multiple servers, or only function for exact deduplication. In this paper, we present a single-server protocol for cross-user nearly-identical deduplication based on secure LSH (SLSH). We formally define our ideal security, and rigorously prove our protocol secure against fully malicious, colluding adversaries with a proof by simulation. We show experimentally that the individual parts of the protocol are computationally feasible, and further discuss practical issues of security and efficiency.