Few-shot learning (FSL) through the training of few labeled samples in the source domain and fine-tuning in target domain has gotten increasing attention in hyperspectral images (HSI) classification. However, in current FSL for HSI classification (HSIC), the number of classes trained in the source domain feature extractor is contingent upon the aligned class number with task classes, which restricts the availability and generalization of the transferable knowledge learned in the source domain. In this article, we propose a few-shot learning with class-number non-aligned training and feature differential network for hyperspectral image classification. Firstly, a class-number non-aligned FSL training framework on multiple independent sources is established, where each source trains respective classes, eliminating the need for aligning the number of classes with the target's. Secondly, in order to learn the feature brought by different domains at different scales, an attention-guided cross-scale feature differential network is constructed to obtain feature differentials between neighboring layers through a feature differential unit (FDU), which extracts detailed pixel's differential information and facilitates to exploit feature variations at different scales. Furthermore, to alleviate the training burden generated by multiple source domains from the non-aligned training strategy, a hybrid loss function is devised to augment the inter-class distance while reducing the intra-class distance. Experiments conducted on three public hyperspectral datasets demonstrate that the proposed model outperforms existing FSL methods for Hyperspectral image classification.

Binary code similarity comparison is a methodology for identifying similar or identical code fragments in binary programs. It is indispensable in fields of software engineering and security, which has many important applications (e.g., plagiarism detection, bug detection). With the widespread of smart and Internet of Things (IoT) devices, an increasing number of programs are ported to multiple architectures (e.g., ARM, MIPS). It becomes necessary to detect similar binary code across architectures as well. The main challenge of this topic lies in the semantics-equivalent code transformation resulting from different compilation settings, code obfuscation, and varied instruction set architectures. Another challenge is the trade-off between comparison accuracy and coverage. Unfortunately, existing methods still heavily rely on semantics-less code features which are susceptible to the code transformation. Additionally, they perform the comparison merely either in a static or in a dynamic manner, which cannot achieve high accuracy and coverage simultaneously. In this paper, we propose a semantics-based hybrid method to compare binary function similarity. We execute the reference function with test cases, then emulate the execution of every target function with the runtime information migrated from the reference function. Semantic signatures are extracted during the execution as well as the emulation. Lastly, similarity scores are calculated from the signatures to measure the likeness of functions. We have implemented the method in a prototype system designated as BinMatch which performs binary code similarity comparison across architectures of x86, ARM and MIPS on the Linux platform. We evaluate BinMatch with nine real-word projects compiled with different compilation settings, on variant architectures, and with commonly-used obfuscation methods, totally performing over 100 million pairs of function comparison. The experimental results show that BinMatch is resilient to the semantics-equivalent code transformation. Besides, it not only covers all target functions for similarity comparison, but also improves the accuracy comparing to the state-of-the-art solutions.

The discriminative correlation filter (DCF) method is widely used in target tracking due to its real‐time performance. However, the computational efficiency of DCF results in boundary effect, which reduces the tracking accuracy in fast motion scene. Besides, background noise is always required to be carefully handled for they will cause trouble in scenes such as background clutter, occlusion, deformation etc. To address the two issues, this study proposes masked discriminative correlation filter, which uses mask to process DCF filter as well as target samples so as to suppress boundary effect and background noise. Experimental results on benchmark datasets show that the proposed tracker performs better than a series of benchmark trackers, and is superior to them in almost various scenes.

The increasing usage of third-party libraries in Android apps is double-edged, boosting the development but introducing extra code base and potential vulnerabilities. Unlike desktop operating systems, Android does not support the sharing of third-party libraries between different apps. Thus both the de-duplicating and the updating of those libraries are difficult to be managed in a unified way. In this paper, we propose a third-party library sharing method to address the issues of code bloating and obsolete code updating. Our approach separates all integrated third-party libraries from app code and makes them still accessible through a dynamic loading mechanism. The separated libraries are managed centrally and can be shared by different apps. This not only saves the storage but also guarantees a prompt update of outdated libraries for every app. We implement APPCOMMUNE, a novel app installation and execution infrastructure to support the proposed third-party library sharing without modifying the commodity Android system. Our experiments with 212 popular third-party libraries and 502 real-world Android apps demonstrate the feasibility and efficiency: all apps work stably with our library sharing model, and 11.1% storage and bandwidth are saved for app downloading and installation. In addition, APPCOMMUNE updates 86.4% of the managed third-party libraries (with 44.6% to the latest versions).

Binary code clone analysis is an important technique which has a wide range of applications in software engineering (e.g., plagiarism detection, bug detection). The main challenge of the topic lies in the semantics-equivalent code transformation (e.g., optimization, obfuscation) which would alter representations of binary code tremendously. Another challenge is the trade-off between detection accuracy and coverage. Unfortunately, existing techniques still rely on semantics-less code features which are susceptible to the code transformation. Besides, they adopt merely either a static or a dynamic approach to detect binary code clones, which cannot achieve high accuracy and coverage simultaneously. In this paper, we propose a semantics-based hybrid approach to detect binary clone functions. We execute a template binary function with its test cases, and emulate the execution of every target function for clone comparison with the runtime information migrated from that template function. The semantic signatures are extracted during the execution of the template function and emulation of the target function. Lastly, a similarity score is calculated from their signatures to measure their likeness. We implement the approach in a prototype system designated as BinMatch which analyzes IA-32 binary code on the Linux platform. We evaluate BinMatch with eight real-world projects compiled with different compilation configurations and commonly-used obfuscation methods, totally performing over 100 million pairs of function comparison. The experimental results show that BinMatch is robust to the semantics-equivalent code transformation. Besides, it not only covers all target functions for clone analysis, but also improves the detection accuracy comparing to the state-of-the-art solutions.

Smart mobile devices are becoming the main vessel of personal privacy information. While they carry valuable information, data erasure is somehow much more vulnerable than was predicted. The security mechanisms provided by the Android system are not flexible enough to thoroughly delete sensitive data. In addition to the weakness among several provided data-erasing and file-deleting mechanisms, we also target the Android OS design flaws in data erasure, and unveil that the design of the Android OS contradicts some secure data-erasure demands. We present the data-erasure flaws in three typical scenarios on mainstream Android devices, such as the data clearing flaw , application uninstallation flaw , and factory reset flaw . Some of these flaws are inherited data-deleting security issues from the Linux kernel, and some are new vulnerabilities in the Android system. Those scenarios reveal the data leak points in Android systems. Moreover, we reveal that the data remanence on the disk is rarely affected by the user’s daily operation, such as file deletion and app installation and uninstallation, by a real-world data deletion latency experiment. After one volunteer used the Android phone for 2 months, the data remanence amount was still considerable. Then, we proposed DataRaider for file recovering from disk fragments. It adopts a file-carving technique and is implemented as an automated sensitive information recovering framework. DataRaider is able to extract private data in a raw disk image without any file system information, and the recovery rate is considerably high in the four test Android phones. We propose some mitigation for data remanence issues, and give the users some suggestions on data protection in Android systems.

Enforcing security on various implementations of OAuth in Android apps should consider a wide range of issues comprehensively. OAuth implementations in Android apps differ from the recommended specification due to the provider and platform factors, and the varied implementations often become vulnerable. Current vulnerability assessments on these OAuth implementations are ad hoc and lack a systematic manner. As a result, insecure OAuth implementations are still widely used and the situation is far from optimistic in many mobile app ecosystems.

Linear phase paraunitary filter bank (LPPUFB) with regular property, i.e. regular LPPUFB (RLPPUFB), can be efficiently designed via lattice structure. The key to the design of such filter bank is to formulate an easy-to-handle regular condition in terms of the lattice structure of LPPUFB, and the solution for the case with even decimation factor has been published. In this letter, a method is proposed to design RLPPUFB with odd decimation factor. First, small part of the free parameters in the lattice structure of LPPUFB is discarded. Then, the lattice structure is equivalently converted to a new one for which the easy-to-handle regular condition can be easily obtained. In contrast to a simple method that discards about a half of the free parameters, the proposed method only discards small part of the free parameters and it therefore can produce better RLPPUFBs.

Multidimensional linear phase perfect reconstruction filter bank (MDLPPRFB) can be designed and implemented via lattice structure. The lattice structure for the MDLPPRFB with filter support N(MΞ) has been published by Muramatsu , where M is the decimation matrix, Ξ is a positive integer diagonal matrix, and N(N) denotes the set of integer vectors in the fundamental parallelepiped of the matrix N. Obviously, if Ξ is chosen to be other positive diagonal matrices instead of only positive integer ones, the corresponding lattice structure would provide more choices of filter banks, offering better trade-off between filter support and filter performance. We call such resulted filter bank as generalized-support MDLPPRFB (GSMDLPPRFB). The lattice structure for GSMDLPPRFB, however, cannot be designed by simply generalizing the process that Muramatsu employed. Furthermore, the related theories to assist the design also become different from those used by Muramatsu . Such issues will be addressed in this paper. To guide the design of GSMDLPPRFB, the necessary and sufficient conditions are established for a generalized-support multidimensional filter bank to be linear-phase. To determine the cases we can find a GSMDLPPRFB, the necessary conditions about the existence of it are proposed to be related with filter support and symmetry polarity (i.e., the number of symmetric filters ns and antisymmetric filters na). Based on a process (different from the one Muramatsu used) that combines several polyphase matrices to construct the starting block, one of the core building blocks of lattice structure, the lattice structure for GSMDLPPRFB is developed and shown to be minimal. Additionally, the result in this paper includes Muramatsu's as a special case.

This paper focuses on the construction of multidimensional biorthogonal multiwavelets and the perfect reconstruction multifilter banks. Based on the Hermite-Neville filter, two lifting structures have been proposed and systematically investigated, and a general design framework has been developed for building biorthogonal multiwavelets and Hermite interpolation filter banks with any multiplicity for any lattice in any dimension with any number of primal and dual vanishing moments. The construction is an important generalization of the Neville-based lifting scheme and inherits all of the advantages of lifting schemes such as fast transform, in-place computation and integer-to-integer transforms. Our multiwavelet systems preserve most of the desirable properties for applications, such as interpolating, short support, symmetry, and high vanishing moments.