Reference counting (refcounting) is widely used in Linux kernel. However, it requires manual operations on the related APIs. In practice, missing or improperly invoking these APIs has introduced too many bugs, known as refcounting bugs. To evaluate the severity of these bugs in history and in future, this paper presents a comprehensive study on them.

Sign language recognition (SLR) bridges the communication gap between the hearing-impaired and the ordinary people. However, existing SLR systems either cannot provide continuous recognition or suffer from low recognition accuracy due to the difficulty of sign segmentation and the insufficiency of capturing both finger and arm motions. The latest system, SignSpeaker, has a significant limit in recognizing two-handed signs with onlyonesmartwatch. To address these problems, this paper designs a novel real-time end-to-end SLR system, called DeepSLR, to translate sign language into voices to help people “hear” sign language. Specifically, two armbands embedded with an IMU sensor and multi-channel sEMG sensors are attached on the forearms to capture both coarse-grained arm movements and fine-grained finger motions. We propose an attention-based encoder-decoder model with a multi-channel convolutional neural network (CNN) to realize accurate, scalable, and end-to-end continuous SLR without sign segmentation. We have implemented DeepSLR on a smartphone and evaluated its effectiveness through extensive evaluations. The average word error rate of continuous sentence recognition is 10.8 percent, and it takes less than 1.1s for detecting signals and recognizing a sentence with 4 sign words, validating the recognition efficiency and real-time ability of DeepSLR in real-world scenarios.

Abstract With the rapid development of electronic and information technology, Internet of Things (IoT) devices have become extensively utilised in various fields. Increasing attention has been paid to the performance and security analysis of IoT-based services. Dynamic instrumentation is a common process in software analysis for acquiring runtime information. However, due to the limited software and hardware resources in IoT devices, most dynamic instrumentation tools do not support IoT-based services. In this paper, we provide an analysis tool, IoTDIT, to solve the current problem of runtime detection in IoT-based services. IoTDIT employs static analysis andptracesystem calls to obtain dynamic firmware information, which can aid in firmware performance analysis and security detection. We perform experiments to verify the performance and effectiveness of the proposed instrumentation tool.

Factorization Machine (FM) has been a popular approach in supervised predictive tasks, such as click-through rate prediction and recommender systems, due to its great performance and efficiency. Recently, several variants of FM have been proposed to improve its performance. However, most of the state-of-the-art prediction algorithms neglected the field information of features, and they also failed to discriminate the importance of feature interactions due to the problem of redundant features. In this paper, we present a novel algorithm called Attention-over-Attention Field-aware Factorization Machine (AoAFFM) for better capturing the characteristics of feature interactions. Specifically, we propose the field-aware embedding layer to exploit the field information of features, and combine it with the attention-over-attention mechanism to learn both feature-level and interaction-level attention to estimate the weight of feature interactions. Experimental results show that the proposed AoAFFM improves FM and FFM with large margin, and outperforms state-of-the-art algorithms on three public benchmark datasets.

Person re-identification is an important task of matching pedestrians across non-overlapping camera views. In this paper, we exploit a weighted feature descriptor for person re-identification. We firstly compute the weights on the superpixel level via graph-based manifold ranking algorithm, then integrate the computed weights into a patch-based feature descriptor, named local maximal occurrence. Finally, the weighted descriptors are fed into a top-push distance learning to mitigate the cross-view gaps. We evaluate the proposed method on three benchmark datasets iLIDS-VID, PRID 450S and VIPeR. The promising experimental results demonstrate the effectiveness of the proposed method comparing with the state-of-the-arts.

Transferable electronic cash (e-cash) allows the recipient of a coin in a transaction to transfer it in a later payment transaction to the third person. The transferability is a desirable property in many applications. However, in the existing transferable e-cash, the size of coins is constant at the cost of increasing the users' burden and not satisfying the optimal anonymity. On the other hand, the e-cash protocol with optimal anonymity has the drawback that the size of coins grows linearly in the number of transfers. In this paper, a transferable optimal-size e-cash is proposed using a different structure, that is, coins are divided into two parts. The new scheme achieves the optimal anonymity, i.e., it satisfies Observe-then-Receive Full Anonymity (OtR-FA), Spend-then-Observe Full Anonymity (StO-FA) and Spend-then-Receive Full Anonymity (StR-FA). Meanwhile, the users has not to keep in memory the data associated to all past transactions. At last, the security proof of the new scheme is given in the standard model.

The taint analysis method is usually effective for vulnerabilities detection. Existing works mostly care about the accuracy of taint propagation, not considering the time cost. We proposed a novel method to improve the efficiency of taint propagation with indices. Based our method, we have implemented TWalker, an effective vulnerabilities detection tool that enables easy data flow analysis of the real world programs, providing faster taint analysis than other existing works. TWalker has four properties: first, it works directly on the programs without source code; second, it monitors the program's execution and records its necessary context; third, it delivers fine-grained taint analysis, providing fast taint propagation with indices; fourth, it could detect vulnerabilities effectively based on two security property rules. We have evaluated TWalker with several real world programs and compared it with a typical taint analysis tool. The experimental results show that our tool could perform taint propagation much faster than other tool, having better ability for vulnerabilities detection.

Symbolic execution simulates program execution by replacing concrete values with symbolic variables for inputs. It could be used in software behavior analysis, vulnerability detection and software security assessment. In this paper, we analyze the path explosion problem encountered in vulnerability detection with the state-of-the-art symbolic execution technology for large scale file parsing programs. We also propose 4 alleviations to ease the problem, i.e. loop controlling, irrelevant path elimination, path selecting and parallel symbolic execution. Based on these alleviations, we implemented a prototype tool to detect file parsing vulnerability in large scale programs automatically, and evaluate it with a suit of benchmarks chosen from open source programs. Our tool detected not only all reported vulnerabilities of memory overflow in the benchmarks, but also some unreported vulnerabilities. The evaluation results show these alleviations could effectively ease the path explosion problem while analyzing large scale file parsing programs.