This paper proposes an automated blood vessel detection scheme based on adaptive contrast enhancement, feature extraction, and tracing. Feature extraction of small blood vessels is performed by using the standard deviation of Gabor filter responses. Tracing of vessels is done via forward detection, bifurcation identification, and backward verification. Tests over twenty images show that for normal images, the true positive rate (TPR) ranges from 80% to 91%, and their corresponding false positive rates (FPR) range from 2.8% to 5.5%. For abnormal images, the TPR ranges from 73.8% to 86.5% and the FPR ranges from 2.1% to 5.3%, respectively. In comparison with two published solution schemes that were also based on the STARE database, our scheme has lower FPR for the reported TPR measure.

Traffic flow prediction is an important application of the ITS technology. In this paper, we applied non-linear timeseries modeling techniques to analyze a traffic data. Our objective is to investigate the deterministic properties of traffic flow using a nonlinear time series analysis technique. The experiment is performed for inductance loop data collected from the San Antonio freeway system. Our study concludes that the traffic data exhibits chaotic properties and techniques based on phase space dynamics can be used to analyze and predict the traffic flow.

Abstract. Contemporary malware makes extensive use of different techniques such as packing, code obfuscation, polymorphism, and metamorphism, to evade signature-based detection. Traditional signature-based detection technique is hard to catch up with latest malware or unknown malware. Behavior-based detection models are being investigated as a new methodology to defeat malware. This kind of approaches typically relies on system call sequences/graphs to model a malicious specification/pattern. In this paper, we present a new class of attacks, namely "shadow attacks", to evade current behaviorbased malware detectors by partitioning one piece of malware into multiple "shadow processes". None of the shadow processes contains a recognizable malicious behavior specification known to single-process-based malware detectors, yet those shadow processes as an ensemble can still fulfill the original malicious functionality. To demonstrate the feasibility of this attack, we have developed a compiler-level prototype tool, AutoShadow, to automatically generate shadow-process version of malware given the source code of original malware. Our preliminary result has demonstrated the effectiveness of shadow attacks in evading several behavior-based malware analysis/detection solutions in real world. With the increasing adoption of multi-core computers and multi-process programs, malware writers may exploit more such shadow attacks in the future. We hope our preliminary study can foster more discussion and research to improve current generation of behavior-based malware detectors to address this great potential threat before it becomes a security problem of the epidemic proportions.

In this paper we propose a deep neural network model with an encoder-decoder architecture that translates images of math formulas into their LaTeX markup sequences. The encoder is a convolutional neural network (CNN) that transforms images into a group of feature maps. To better capture the spatial relationships of math symbols, the feature maps are augmented with 2D positional encoding before being unfolded into a vector. The decoder is a stacked bidirectional long short-term memory (LSTM) model integrated with the soft attention mechanism, which works as a language model to translate the encoder output into a sequence of LaTeX tokens. The neural network is trained in two steps. The first step is token-level training using the Maximum-Likelihood Estimation (MLE) as the objective function. At completion of the token-level training, the sequence-level training objective function is employed to optimize the overall model based on the policy gradient algorithm from reinforcement learning. Our design also overcomes the exposure bias problem by closing the feedback loop in the decoder during sequence-level training, i.e., feeding in the predicted token instead of the ground truth token at every time step. The model is trained and evaluated on the IM2LATEX-100K dataset and shows state-of-the-art performance on both sequence-based and imagebased evaluation metrics.

No abstract