On query result integrity over encrypted data by Esiner, Ertem, Datta, Anwitaman

“…Our contribution is in bridging two independent lines of work (searchable encryption, and provable data possession) resulting in a general purpose technique, which does so without increasing the client storage overhead, while only a small token and a data structure is added to the server side (in comparison to a base searchable encryption without mechanisms for determining result integrity), where the data structure can simultaneously also be used for integrity checks on the stored data.…”
Get full text
Get full text

Distributed partial clustering by Guha, Sudipto, Li, Yi, Zhang, Qin

“…Recent years have witnessed an increasing popularity of algorithm design for distributed data, largely due to the fact that massive datasets are often collected and stored in different locations. In the distributed setting, communication typically dominates the query processing time. …”
Get full text

Two-factor authentication for trusted third party free dispersed storage by Esiner, Ertem, Datta, Anwitaman

“…It is achieved by the application of data dispersal, encryption as well as two-factor (knowledge and possession) based authentication and access control techniques so that unauthorized parties (attackers) or a small set of colluding servers cannot gain access to the stored data. The protocol design takes into account usability issues as opposed to the closest prior work Esiner and Datta (2016). …”
Get full text
Get full text

Mapping entity sets in news archives across time by Duan, Yijun, Jatowt, Adam, Bhowmick, Sourav S., Yoshikawa, Masatoshi

“…We propose a novel way of utilizing and accessing information stored in news archives as well as a new style of investigating the history. …”
Get full text

Generation of 3D building models from city area maps by Martel, Roman, Erdt, Marius, Dong, Chaoqun, Chen, Kan, Johan, Henry

“…The city area maps were recorded and stored over a long time period. This imposes several challenges to the pipeline such as different font styles of typewriters, handwritings of different persons, varying layout, low contrast, damages and scanning artifacts. …”
Get full text
Get full text

Evolutionary multi-task learning for modular knowledge representation in neural networks by Chandra, Rohitash, Gupta, Abhishek, Ong, Yew-Soon, Goh, Chi-Keong

“…Modularity ensures that the knowledge is stored in a manner where any complications in certain modules do not affect the overall functionality of the brain. …”
Get full text

An interclass margin maximization learning algorithm for evolving spiking neural network by Dora, Shirin, Sundaram, Suresh, Sundararajan, Narasimhan

“…The normalized membrane potential learning rule considers both the local information in the spike train generated by a presynaptic neuron and the existing knowledge (synaptic weights) stored in the network to update the synaptic weights. …”
Get full text

Layered Security for Storage at the Edge: On Decentralized Multi-factor Access Control by Esiner, Ertem, Datta, Anwitaman

“…We also extend the basic protocol to demonstrate how collaboration can be supported even while the stored content is encrypted, and where each collaborator is still restrained from accessing the data through a multi-factor access mechanism. …”
Get full text
Get full text

Embedding QR codes onto B-spline surfaces for 3D printing by Kikuchi, Ryosuke, Yoshikawa, Sora, Jayaraman, Pradeep Kumar, Zheng, Jianmin, Maekawa, Takashi

“…Quick Response (QR) code which is a two-dimensional matrix barcode invented by Denso, a Japanese automotive industry, in 1994, can be used for this purpose. It can store more data than the 1D barcode in a smaller space, and using a smartphone as a scanner, one can directly visit a website where all the information of the parts is stored. …”
Get full text

Search and permission request over encrypted database by Tjuawinata, Ivan, Zhao, Yongjun, Shen, Bowen, Lam, Kwok-Yan, Chi, Chi-Hung

“…In this work, we consider a basic scenario where shared data are stored in an encrypted database while still allowing for search requests and permission verification. …”
Get full text

Feasibility structure modeling : an effective chaperone for constrained memetic algorithms by Handoko, Stephanus Daniel, Kwoh, Chee Keong, Ong, Yew-Soon

“…As more solutions are generated and subsequently stored in the database, the feasibility structure can thus be approximated more accurately. …”
Get full text

Compressed representation for higher-level meme space evolution : a case study on big knapsack problems by Feng, Liang, Gupta, Abhishek, Ong, Yew-Soon

“…In today’s world, with the rapid growth in communication and computation technologies, massive volumes of data are generated and stored daily, making it vital to explore learning and optimization techniques that can handle ‘big’ problems. …”
Get full text

Learning feature embedding refiner for solving vehicle routing problems by Li, Jingwen, Ma, Yining, Cao, Zhiguang, Wu, Yaoxin, Song, Wen, Zhang, Jie, Chee, Yeow Meng

“…The former extracts dynamic graph topological information of historical solutions stored in a diversified solution pool to generate aggregated pool embeddings that are further improved by the GRU, and the latter adaptively refines the feature embeddings from the encoder with the guidance of the improved pool embeddings. …”
Get full text

FedVision : an online visual object detection platform powered by federated learning by Liu, Yang, Huang, Anbu, Luo, Yun, Huang, He, Liu, Youzhi, Chen, Yuanyuan, Feng, Lican, Chen, Tianjian, Yu, Han, Yang, Qiang

“…However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored large training datasets following the current approach. …”
Get full text

Semi-supervised federated heterogeneous transfer learning by Feng, Siwei, Li, Boyang, Yu, Han, Liu, Yang, Yang, Qiang

“…Federated learning (FL) is a privacy-preserving paradigm that collaboratively train machine learning models with distributed data stored in different silos without exposing sensitive information. …”
Get full text

An efficient sparse LSTM accelerator on embedded FPGAs with bandwidth-oriented pruning by Li, Shiqing, Zhu, Shien, Luo, Xiangzhong, Luo, Tao, Liu, Weichen

“…Considering that weights are stored in the off-chip DDR, the performance of LSTM is bounded by the available memory bandwidth. …”
Get full text

Hierarchical vectorization for facial images by Fu, Qian, Liu, Linlin, Hou, Fei, He, Ying

“…While portraits are commonly captured and stored as raster images, editing raster images is non-trivial and requires the user to be highly skilled. …”
Get full text

Privacy and robustness in federated learning: attacks and defenses by Lyu, Lingjuan, Yu, Han, Ma, Xingjun, Chen, Chen, Sun, Lichao, Zhao, Jun, Yang, Qiang, Yu, Philip S.

“…As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. …”
Get full text

Use B-factor related features for accurate classification between protein binding interfaces and crystal packing contacts by Liu, Qian, Li, Zhenhua, Li, Jinyan

“…Our computational methods have a potential for large-scale and accurate identification of biological interactions from the experimentally determined structural data stored at PDB which may have diverse interface sizes.…”
Get full text
Get full text

When information freshness meets service latency in federated learning : a task-aware incentive scheme for smart industries by Lim, Bryan Wei Yang, Xiong, Zehui, Kang, Jiawei, Niyato, Dusit, Leung, Cyril, Miao, Chunyan, Shen, Xuemin

“…In our system model, a model owner initiates an FL task involving a group of workers, i.e., data owners, to perform model training on their locally stored data before transmitting the model updates for aggregation. …”
Get full text