Biblio

The cutting-edge biometric recognition systems extract distinctive feature vectors of biometric samples using deep neural networks to measure the amount of (dis-)similarity between two biometric samples. Studies have shown that personal information (e.g., health condition, ethnicity, etc.) can be inferred, and biometric samples can be reconstructed from those feature vectors, making their protection an urgent necessity. State-of-the-art biometrics protection solutions are based on homomorphic encryption (HE) to perform recognition over encrypted feature vectors, hiding the features and their processing while releasing the outcome only. However, this comes at the cost of those solutions' efficiency due to the inefficiency of HE-based solutions with a large number of multiplications; for (dis-)similarity measures, this number is proportional to the vector's dimension. In this paper, we tackle the HE performance bottleneck by freeing the two common (dis-)similarity measures, the cosine similarity and the squared Euclidean distance, from multiplications. Assuming normalized feature vectors, our approach pre-computes and organizes those (dis-)similarity measures into lookup tables. This transforms their computation into simple table-lookups and summation only. We study quantization parameters for the values in the lookup tables and evaluate performances on both synthetic and facial feature vectors for which we achieve a recognition performance identical to the non-tabularized baseline systems. We then assess their efficiency under HE and record runtimes between 28.95ms and 59.35ms for the three security levels, demonstrating their enhanced speed.

In healthcare 4.0 ecosystems, authentication of healthcare information allows health stakeholders to be assured that data is originated from correct source. Recently, biometric based authentication is a preferred choice, but as the templates are stored on central servers, there are high chances of copying and generating fake biometrics. An adversary can forge the biometric pattern, and gain access to critical health systems. Thus, to address the limitation, the paper proposes a scheme, PHBio, where an encryption-based biometric system is designed prior before storing the template to the server. Once a user provides his biometrics, the authentication process does not decrypt the data, rather uses a homomorphic-enabled Paillier cryptosystem. The scheme presents the encryption and the comparison part which is based on euclidean distance (EUD) strategy between the user input and the stored template on the server. We consider the minimum distance, and compare the same with a predefined threshold distance value to confirm a biometric match, and authenticate the user. The scheme is compared against parameters like accuracy, false rejection rates (FARs), and execution time. The proposed results indicate the validity of the scheme in real-time health setups.

The impact of digital gadgets is enormous in the current Internet world because of the easy accessibility, flexibility and time-saving benefits for the consumers. The number of computer users is increasing every year. Meanwhile, the time spent and the computers also increased. Computer users browse the internet for various information gathering and stay on the internet for a long time without control. Nowadays working people from home also spend time with the smart devices, computers, and laptops, for a longer duration to complete professional work, personal work etc. the proposed study focused on deriving the impact factors of Smartphones by analyzing the keystroke dynamics Based on the usage pattern of keystrokes the system evaluates the stress level detection using machine learning techniques. In the proposed study keyboard users are intended for testing purposes. Volunteers of 200 members are collectively involved in generating the test dataset. They are allowed to sit for a certain frame of time to use the laptop in the meanwhile the keystroke of the Mouse and keyboard are recorded. The system reads the dataset and trains the model using the Dynamic Cat-Boost algorithm (DCB), which acts as the classification model. The evaluation metrics are framed by calculating Euclidean distance (ED), Manhattan Distance (MahD), Mahalanobis distance (MD) etc. Quantitative measures of DCB are framed through Accuracy, precision and F1Score.

In the present paper, the application of filtering methods to select features when detecting email spam using the K-NN classifier is examined. The experiments include computation of the accuracy and F-measure of the e-mail texts classification with different methods for feature selection, different number of selected features and two ways to find the distance between dataset examples when executing K-NN classifier - Euclidean distance and cosine similarity. The obtained results are summarized and analyzed.

This paper proposes an efficient face template protection system based on homomorphic encryption. By developing a message packing method suitable for the calculation of the squared Euclidean distance, the proposed system computes the squared Euclidean distance between facial features by a single homomorphic multiplication. Our experimental results show the transaction time of the proposed system is about 14 times faster than that of the existing face template protection system based on homomorphic encryption presented in BIOSIG2020.

Fast search of hyperspectral data is crucial in many practical applications ranging from classification to finding duplicate fragments in images. In this paper, we evaluate two space partitioning data structures in the task of searching hyperspectral data. In particular, we consider vp-trees and ball-trees, study several tree construction algorithms, and compare these structures with the brute force approach. In addition, we evaluate vp-trees and ball-trees with four similarity measures, namely, Euclidean Distance, Spectral Angle Mapper Bhattacharyya Angle, and Hellinger distance.

The advance of smart eHealthcare and cloud computing techniques has propelled an increasing number of healthcare centers to outsource their healthcare data to the cloud. Meanwhile, in order to preserve the privacy of the sensitive information, healthcare centers tend to encrypt the data before outsourcing them to the cloud. Although the data encryption technique can preserve the privacy of the data, it inevitably hinders the query functionalities over the outsourced data. Among all practical query functionalities, the similarity range query is one of the most popular ones. However, to our best knowledge, many existing studies on the similarity range query over outsourced data still suffer from the efficiency issue in the query process. Therefore, in this paper, aiming at improving the query efficiency, we propose an efficient privacy-preserving similarity range query scheme based on the precomputed distance technique. In specific, we first introduce a pre-computed distance based similarity range query (PreDSQ) algorithm, which can improve the query efficiency by precomputing some distances. Then, we propose our privacy-preserving similarity query scheme by applying an asymmetric scalar-product-preserving encryption technique to preserve the privacy of the PreDSQ algorithm. Both security analysis and performance evaluation are conducted, and the results show that our proposed scheme is efficient and can well preserve the privacy of data records and query requests.

We investigate a prediction model using RNN for network intrusion detection in industrial IoT environments. For intrusion detection, we use anomaly detection methods that estimate the next packet, measure and score the distance measurement in real packets to distinguish whether it is a normal packet or an abnormal packet. When the packet was learned in the LSTM model, two-gram and sliding window of N-gram showed the best performance in terms of errors and the performance of the LSTM model was the highest compared with other data mining regression techniques. Finally, cosine similarity was used as a scoring function, and anomaly detection was performed by setting a boundary for cosine similarity that consider as normal packet.

In Compositional data, the relative proportions of the components contain important relevant information. In such case, Euclidian distance fails to capture variation when considered within data science models and approaches such as partial least squares discriminant analysis (PLS-DA). Indeed, the Euclidean distance assumes implicitly that the data is normally distributed which is not the case of compositional vectors. Aitchison transformation has been considered as a standard in compositional data analysis. In this paper, we consider two other transformation methods, Isometric log ratio (ILR) transformation and data-based power (alpha) transformation, before feeding the data to PLS-DA algorithm for classification [1]. In order to investigate the merits of both methods, we apply them in two challenging information system security applications namely spam filtering and intrusion detection.

Due to the leakage of privacy information in the sensitive region of trajectory anonymity publishing, which is resulted by the attack, this paper aims at the trajectory anonymity algorithm of division of region. According to the start stop time of the trajectory, the current sensitive region is found with the k-anonymity set on the synchronous trajectory. If the distance between the divided sub-region and the adjacent anonymous area is not greater than the threshold d, the area will be combined. Otherwise, with the guidance of location mapping, the forged location is added to the sub-region according to the original location so that the divided sub-region can meet the principle of k-anonymity. While the forged location retains the relative position of each point in the sensitive region, making that the divided sub-region and the original Regional anonymity are consistent. Experiments show that compared with the existing trajectory anonymous algorithm and the synchronous trajectory data set with the same privacy, the algorithm is highly effective in both privacy protection and validity of data quality.

Video retrieval technology faces a series of challenges with the tremendous growth in the number of videos. In order to improve the retrieval performance in efficiency and accuracy, a novel deep hash method for video data hierarchical retrieval is proposed in this paper. The approach first uses cluster-based method to extract key frames, which reduces the workload of subsequent work. On the basis of this, high-level semantical features are extracted from VGG16, a widely used deep convolutional neural network (deep CNN) model. Then we utilize a hierarchical retrieval strategy to improve the retrieval performance, roughly can be categorized as coarse search and fine search. In coarse search, we modify simHash to learn hash codes for faster speed, and in fine search, we use the Euclidean distance to achieve higher accuracy. Finally, we compare our approach with other two methods through practical experiments on two videos, and the results demonstrate that our approach has better retrieval effect.

Differential privacy is heavily used in privacy protection due to it provides strong protection against private data. The existing differential privacy scheme mainly implements the privacy protection of nodes or edges in the network by perturbing the data query results. Most of them cannot meet the privacy protection requirements of multiple types of information. In order to overcome these issues, a differential privacy security mechanism with average path length (APL) query is proposed in this paper, which realize the privacy protection of both network vertices and edge weights. Firstly, by describing APL, the reasons for choosing this attribute as the query function are analyzed. Secondly, global sensitivity of APL query under the need of node privacy protection and edge-weighted privacy protection is proved. Finally, the relationship between data availability and privacy control parameters in differential privacy is analyzed through experiments.

A main issue in approximate nearest neighbor search is to achieve an excellent tradeoff between search accuracy and computation cost. In this paper, we address this issue by leveraging k-nearest neighbor graph and hill-climbing to accelerate vector quantization in the query assignment process. A modified hill-climbing algorithm is proposed to traverse k-nearest neighbor graph to find closest centroids for a query, rather than calculating the query distances to all centroids. Instead of using random seeds in the original hill-climbing algorithm, we generate high-quality seeds based on the hashing technique. It can boost the query assignment efficiency due to a better start-up in hill-climbing. We evaluate the experiment on the benchmarks of SIFT1M and GIST1M datasets, and show the proposed hashing-based seed generation effectively improves the search performance.

A major challenge for utilities is energy theft, wherein malicious actors steal energy for financial gain. One such form of theft in the smart grid is the fraudulent amplification of energy generation measurements from DERs, such as photo-voltaics. It is important to detect this form of malicious activity, but in a way that ensures the privacy of customers. Not considering privacy aspects could result in a backlash from customers and a heavily curtailed deployment of services, for example. In this short paper, we present a novel privacy-preserving approach to the detection of manipulated DER generation measurements.

Mobile payment has drawn considerable attention due to its convenience of paying via personal mobile devices at anytime and anywhere, and passcodes (i.e., PINs or patterns) are the first choice of most consumers to authorize the payment. This paper demonstrates a serious security breach and aims to raise the awareness of the public that the passcodes for authorizing transactions in mobile payments can be leaked by exploiting the embedded sensors in wearable devices (e.g., smartwatches). We present a passcode inference system, WristSpy, which examines to what extent the user's PIN/pattern during the mobile payment could be revealed from a single wrist-worn wearable device under different passcode input scenarios involving either two hands or a single hand. In particular, WristSpy has the capability to accurately reconstruct fine-grained hand movement trajectories and infer PINs/patterns when mobile and wearable devices are on two hands through building a Euclidean distance-based model and developing a training-free parallel PIN/pattern inference algorithm. When both devices are on the same single hand, a highly challenging case, WristSpy extracts multi-dimensional features by capturing the dynamics of minute hand vibrations and performs machine-learning based classification to identify PIN entries. Extensive experiments with 15 volunteers and 1600 passcode inputs demonstrate that an adversary is able to recover a user's PIN/pattern with up to 92% success rate within 5 tries under various input scenarios.

Searchable Encryption (SE) schemes provide security and privacy to the cloud data. The existing SE approaches enable multiple users to perform search operation by using various schemes like Broadcast Encryption (BE), Attribute-Based Encryption (ABE), etc. However, these schemes do not allow multiple users to perform the search operation over the encrypted data of multiple owners. Some SE schemes involve a Proxy Server (PS) that allow multiple users to perform the search operation. However, these approaches incur huge computational burden on PS due to the repeated encryption of the user queries for transformation purpose so as to ensure that users' query is searchable over the encrypted data of multiple owners. Hence, to eliminate this computational burden on PS, this paper proposes a secure proxy server approach that performs the search operation without transforming the user queries. This approach also returns the top-k relevant documents to the user queries by using Euclidean distance similarity approach. Based on the experimental study, this approach is efficient with respect to search time and accuracy.

We, humans, have the ability to easily imagine scenes that depict sentences such as ``Today is a beautiful sunny day'' or ``There is a Christmas feel, in the air''. While it is hard to precisely describe what one person may imagine, the essential high-level themes associated with such sentences largely remains the same. The ability to synthesize novel images that depict the feel of a sentence is very useful in a variety of applications such as education, advertisement, and entertainment. While existing papers tackle this problem given a style image, we aim to provide a far more intuitive and easy to use solution that synthesizes novel renditions of an existing image, conditioned on a given sentence. We present a method for cross-modal style transfer between an English sentence and an image, to produce a new image that imbibes the essential theme of the sentence. We do this by modifying the style transfer mechanism used in image style transfer to incorporate a style component derived from the given sentence. We demonstrate promising results using the YFCC100m dataset.

Side-channel collision attacks have been one of the most powerful attack techniques, combining advantages of traditional side-channel attack and mathematical cryptanalysis. In this paper, we propose a novel multiple-bits side-channel collision attack based on double distance voting detection, which can find all 120 relations among 16 key bytes with only 32 averaged power traces when applied to AES (Advanced Encryption Standard) algorithm. Practical attack experiments are performed successfully on a hardware implementation of AES on FPGA board. Results show that the necessary number of traces for our method is about 50% less than correlation-enhanced collision attack and 76% less than binary voting test with 90% success rate.

A wireless sensor network (WSN) is composed of sensor nodes and a base station. In WSNs, constructing an efficient key-sharing scheme to ensure a secure communication is important. In this paper, we propose a new key-sharing scheme for groups, which shares a group key in a single broadcast without being dependent on the number of nodes. This scheme is based on geometric characteristics and has information-theoretic security in the analysis of transmitted data. We compared our scheme with conventional schemes in terms of communication traffic, computational complexity, flexibility, and security, and the results showed that our scheme is suitable for an Internet-of-Things (IoT) network.

Cloud computing enables the outsourcing of big data analytics, where a third-party server is responsible for data management and processing. In this paper, we consider the outsourcing model in which a third-party server provides record matching as a service. In particular, given a target record, the service provider returns all records from the outsourced dataset that match the target according to specific distance metrics. Identifying matching records in databases plays an important role in information integration and entity resolution. A major security concern of this outsourcing paradigm is whether the service provider returns the correct record matching results. To solve the problem, we design EARRING, an Efficient Authentication of outsouRced Record matchING framework. EARRING requires the service provider to construct the verification object (VO) of the record matching results. From the VO, the client is able to catch any incorrect result with cheap computational cost. Experiment results on real-world datasets demonstrate the efficiency of EARRING.