Binary Code Similarity Detection (BCSD) is significant for software security as it can address binary tasks such as malicious code snippets identification and binary patch analysis by comparing code patterns. Recently, there has been a growing focus on artificial intelligence-based approaches in BCSD due to their scalability and generalization. Because binaries are compiled with different compilation configurations, existing approaches still face notable limitations when comparing binary similarity. First, BCSD requires analysis on code behavior, and existing work claims to extract semantic, but actually still makes analysis in terms of syntax. Second, directly extracting features from assembly sequences, existing work cannot address the issues of instruction reordering and different syntax expressions caused by various compilation configurations. In this paper, we propose STRTUNE, which slices binary code based on data dependence and perform slice-level fine-tuning. To address the first limitation, STRTUNE performs backward slicing based on data dependence to capture how a value is computed along the execution. Each slice reflects the collecting semantics of the code, which is stable across different compilation configurations. STRTUNE introduces flow types to emphasize the independence of computations between slices, forming a graph representation. To overcome the second limitation, based on slices corresponding to the same value computation but having different syntax representation, STRTUNE utilizes a Siamese Network to fine-tune such pairs, making their representations closer in the feature space. This allows the cross-graph attention to focus more on the matching of similar slices based on slice contents and flow types involved. Our evaluation results demonstrate the effectiveness and practicality of STRTUNE. We show that STRTUNE outperforms the state-of-the-art methods for BCSD, achieving a Recall@1 that is 25.3% and 22.2% higher than jTrans and GMN in the task of function retrieval cross optimization in x64.

Classifying and accurately locating a visual category with few annotated training samples in computer vision has motivated the few-shot object detection technique, which exploits transfering the source-domain detection model to the target domain. Under this paradigm, however, such transferred source-domain detection model usually encounters difficulty in the classification of the target domain because of the low data diversity of novel training samples. To combat this, we present a simple yet effective few-shot detector, Transferable RCNN. To transfer general knowledge learned from data-abundant base classes to data-scarce novel classes, we propose a weight transfer strategy to promote model transferability and an attention-based feature enhancement mechanism to learn more robust object proposal feature representations. Further, we ensure strong discrimination by optimizing the contrastive objectives of feature maps via a supervised spatial contrastive loss. Meanwhile, we introduce an angle-guided additive margin classifier to augment instance-level inter-class difference and intra-class compactness, which is beneficial for improving the discriminative power of the few-shot classification head under a few supervisions. Our proposed framework outperforms the current works in various settings of PASCAL VOC and MSCOCO datasets; this demonstrates the effectiveness and generalization ability.

Real-time and accurate measurement of coal quantity is the key to energy-saving and speed regulation of belt conveyor. The electronic belt scale and the nuclear scale are the commonly used methods for detecting coal quantity. However, the electronic belt scale uses contact measurement with low measurement accuracy and a large error range. Although nuclear detection methods have high accuracy, they have huge potential safety hazards due to radiation. Due to the above reasons, this paper presents a method of coal quantity detection and classification based on machine vision and deep learning. This method uses an industrial camera to collect the dynamic coal quantity images of the conveyor belt irradiated by the laser transmitter. After preprocessing, skeleton extraction, laser line thinning, disconnection connection, image fusion, and filling, the collected images are processed to obtain coal flow cross-sectional images. According to the cross-sectional area and the belt speed of the belt conveyor, the coal volume per unit time is obtained, and the dynamic coal quantity detection is realized. On this basis, in order to realize the dynamic classification of coal quantity, the coal flow cross-section images corresponding to different coal quantities are divided into coal type images to establish the coal quantity data set. Then, a Dense-VGG network for dynamic coal classification is established by the VGG16 network. After the network training is completed, the dynamic classification performance of the method is verified through the experimental platform. The experimental results show that the classification accuracy reaches 94.34%, and the processing time of a single frame image is 0.270[Formula: see text]s.

MOTIVATION: Repeats are ubiquitous in genomes and play important roles in evolution. Transposable elements are a common kind of repeat. Transposon insertions can be nested and make the task of identifying repeats difficult. RESULTS: We develop a novel iterative algorithm, called Greedier, to find repeats in a target genome given a repeat library. Greedier distinguishes itself from existing methods by taking into account the fragmentation of repeats. Each iteration consists of two passes. In the first pass, it identifies the local similarities between the repeat library and the target genome. Greedier then builds graphs from this comparison output. In each graph, a vertex denotes a similar subsequence pair. Edges denote pairs of subsequences that can be connected to form higher similarities. In the second pass, Greedier traverses these graphs greedily to find matches to individual repeat units in the repeat library. It computes a fitness value for each such match denoting the similarity of that match. Matches with fitness values greater than a cutoff are removed, and the rest of the genome is stitched together. The similarity cutoff is then gradually reduced, and the iteration is repeated until no hits are returned from the comparison. Our experiments on the Arabidopsis and rice genomes show that Greedier identifies approximately twice as many transposon bases as those found by cross_match and WindowMasker. Moreover, Greedier masks far fewer false positive bases than either cross_match or WindowMasker. In addition to masking repeats, Greedier also reports potential nested transposon structures.

MOTIVATION: We consider the problem of identifying low-complexity regions (LCRs) in a protein sequence. LCRs are regions of biased composition, normally consisting of different kinds of repeats. RESULTS: We define new complexity measures to compute the complexity of a sequence based on a given scoring matrix, such as BLOSUM 62. Our complexity measures also consider the order of amino acids in the sequence and the sequence length. We develop a novel graph-based algorithm called GBA to identify LCRs in a protein sequence. In the graph constructed for the sequence, each vertex corresponds to a pair of similar amino acids. Each edge connects two pairs of amino acids that can be grouped together to form a longer repeat. GBA finds short subsequences as LCR candidates by traversing this graph. It then extends them to find longer subsequences that may contain full repeats with low complexities. Extended subsequences are then post-processed to refine repeats to LCRs. Our experiments on real data show that GBA has significantly higher recall compared to existing algorithms, including 0j.py, CARD, and SEG. AVAILABILITY: The program is available on request.