We describe a subfield attack for NTRU problem by using the symmetric function map Sk, which is a generalization of results presented by Albrecht, Bai and Ducas [1] and Cheon, Jeong and [2]. At first, we prove that Skwith an appropriate k can fits for more cases compared with previous related works while maintaining the same or better efficiency. Then we show the subfield attack has its advantage compared with the subring attack described in [3]. At last we present a method to make the subfield attack algorithm more efficient.

Deep Neural Networks (DNNs) have demonstrated remarkable performance in a diverse range of applications. Along with the prevalence of deep learning, it has been revealed that DNNs are vulnerable to attacks. By deliberately crafting adversarial examples, an adversary can manipulate a DNN to generate incorrect outputs, which may lead catastrophic consequences in applications such as disease diagnosis and self-driving cars. In this paper, we propose an effective method to detect adversarial examples in image classification. Our key insight is that adversarial examples are usually sensitive to certain image transformation operations such as rotation and shifting. In contrast, a normal image is generally immune to such operations. We implement this idea of image transformation and evaluate its performance in oblivious attacks. Our experiments with two datasets show that our technique can detect nearly 99% of adversarial examples generated by the state-of-the-art algorithm. In addition to oblivious attacks, we consider the case of white-box attacks. We propose to introduce randomness in the process of image transformation, which can achieve a detection ratio of around 70%.

An effective way to visualize the prediction of deep neural networks on an image is to decompose the prediction into the contribution of units (pixels or patches). In the existing works, these units are largely considered independently, thus limiting the performance of visualization. In this paper, we propose a new predication visualization method that uses super-pixel as a contribution unit. Moreover, our method takes into consideration of the interaction of adjacent super-pixels. We implement our technique and evaluate its performance with various images. Our results show its excellent performance.

We propose a Parity-based Data Outsourcing(PDO) model in this paper. This model outsources a set of raw data by associating it with a set of parity data and then distributing both sets of data among a number of cloud servers that are managed independently by different service providers. Users query the servers for the data of their interest and are allowed to perform both authentication and correction. The former refers to the capability of verifying if the query result they receive is correct (i.e., all data items that satisfy the query condition are received, and every data item received is original from the data owner), whereas the latter, the capability of correcting the corrupted data, if any. A data item may be corrupted unintentionally (e.g, because of errors in systems and/or networking) or intentionally (e.g., by malicious service providers or because of systems being compromised by hackers). Existing techniques support only query authentication, but not error correction. Moreover, they all rely on complex cryptographic techniques and require the cloud server to build verification objects. In contrast, our approach achieves both without using any encryption. It does not require to install any additional software on a cloud server and thus can take advantage of the many cloud data management services available on the market today. We address the challenges of PDO implementation, including parity coding, database encoding, data retrieval, and database insertion and deletion, and evaluate the performance potential of PDO through analysis, simulation, and prototyping. Our results indicate its excellent performance in terms of storage, communication, and computation overhead.

In mobile object database systems, both query issuers and queried objects are subject to location privacy intrusion. One solution to this problem is to have users reduce their location resolution when making location update. Such location cloaking allows mobile objects to achieve a desired level of protection, but may not produce accurate query results. Alternatively, one can apply cryptography techniques such as secure multiparty computation to compute the spatial relationship among mobile objects without having mobile objects to disclose their location at all. This strategy produces high quality query results, but in general are computation-intensive, especially when a large number of mobile objects are involved. In this paper, we present a hybrid approach that mitigates the above dilemma. Our idea is to compute approximate query results based on cloaked location information and then refine query results by applying homomorphic encryption. We demonstrate that this approach can be used for efficient and privacy-preserving processing of KNN queries and evaluate its performance through simulation.

Technology develops rapidly and information floods. In the information explosion era, what people lack is not the scale of information but how to obtain the needed information quickly and accurately. Personalized search and service emerges. And the key problem is to make clear the needs of the users. In this paper, we combined user interest and collaborative filtering to reorder the search results and implemented the approach using multi-agent technology. Finally, we set up an experiment to check the effect of this method.