With the accelerated development of software, developers face the continuous challenge of fixing vulnerabilities but vulnerability-fixing commits often disassociated from the vulnerabilities, and the structural and semantic differences between code changes and natural language present significant challenges in identifying these commits. Existing approaches utilize machine learning and deep learning techniques to address this problem, but they often do not fully leverage the information about code changes. In this paper, we propose VFProber, a method based on a code change pretrained model, aiming to provide a comprehensive and unified framework for identifying vulnerability-fixing commits. VFProber uses semantic adjustment to distinguish between context-sensitive and context-insensitive code units in code changes, thereby enhancing the model’s understanding of code changes during the training process. Secondly, VFProber employs a novel code change pretrained model as a feature extractor. Compared with ordinary code pretrained models, it can better meet the requirements of the vulnerability-fixing identification task. Moreover, we constructed a vulnerability-fixing dataset containing two common programming languages, Java and JavaScript, from industrial projects. In the experimental section, we designed three tasks to evaluate the method. The results show that, compared with the best baseline, VFProber performs better in the vulnerability-fixing identification task and can effectively reduce false positives and false negatives.

To promptly identify software defects and prevent defective code changes from being integrated into the repository, Just-In-Time Software Defect Prediction (JIT-SDP) has demonstrated promising research findings. Recent studies have begun to utilize Pre-trained Models (PTMs) for training and prediction, yet these models inherently impose input length limitations, leading to forced truncation of inputs. However, previous work has largely overlooked the impact of forced truncation, even though it may inadvertently discard critical input information, leading to degraded model performance. Moreover, some existing methods fail to maintain consistency in truncation during each model construction process, leading to unexplainable truncations and unstable model performance. In addition, previous datasets suffer from limitations and incompleteness. To this end, we construct a large-scale and comprehensive dataset, MC4Defect. Moreover, we propose JIT-Align, which prioritizes code changes within a commit using a semantic alignment algorithm to make full use of the limited input space of PTMs. To evaluate the feasibility of JIT-Align, we first assess the classification capability of our method by comparing it against four baselines across five datasets. Then, we conduct ablation studies on the proposed semantic alignment framework to validate its effectiveness. Experimental results show that JIT-Align, along with its semantic alignment framework, outperforms all baselines in JIT-SDP tasks, with average F1 score improvements of 3.1%-9.6% and MCC increases of 3.1%-9.7% across all projects, exhibiting higher stability and better interpretability compared to alternative approaches.

Real-time semantic segmentation plays a significant role in many real-world applications. However, existing methods usually neglect the importance of aggregating global scene clues and multi-level semantics due to computational limits of mobile devices. To address the above challenges and maintain higher accuracy, we propose an efficient attention-augmented network, namely EANet. Specifically, we first leverage an extremely lightweight attention module called sparse strip attention module (SSAM) to retain global contextual information while greatly reducing computation cost. Moreover, the meticulously designed joint attention fusion module (JAFM) follows an attention strategy to efficiently integrate semantics and details from multi-level features. On Cityscapes test set, our network achieves 74.6% mIoU at 35.4 FPS on a single GTX1080Ti GPU with a 1024×2048-pixel image. Extensive experiments show that our EANet achieves promising results on Cityscapes dataset.

Background Multidrug resistant Acinetobacter baumanii (MRAB) is an emerging pathogen that is an important cause of hospital acquired infection and has been shown to increase mortality and length of hospital stay. MRAB is the predominant multidrug resistant bacteria at Nashville General Hospital at Meharry Medical College (NGHM). The goal of this study is to determine the major genomic and proteomics patterns of MRAB at NGHM.

Background Two hundred and forty-seven isolates of Acinetobacter baumanii (AB) were identified in the Nashville General Hospital at Meharry epidemiology database for a three year period. Of these isolates, 77% were multi-drug resistant (MRAB). Mechanical ventilation and multiple site recovery were associated with MRAB, and MRAB isolates were associated with increased mortality relative to sensitive AB isolates [1]. AB acquires resistance rapidly and the mechanisms are still being identified. Proteomic analysis can identify proteins that change in their expression levels in the presence of antibiotics, a possible mechanism of resistance for AB. No proteome databases exist for this organism so antibiotic sensitivity and resistance proteomes were generated for MRAB bronchial wash isolate MMC#4. Materials and methods AB MMC#4 was grown in plain LB broth or LB broth supplemented with MIC50 concentrations of levofloxacin, tobramycin, gentamicin, cefotaxime and meropenem. Cell pellets were lysed and total protein run on an SDS-PAGE gel. Protein bands were excised and in-gel digested with trypsin. Resulting peptides were analyzed using a Thermo Finnigan LTQ ion trap mass spectrometer equipped with a 1-D nanoLC pump (Eksigent), Nanospray source (James A Hill Company), and Xcalibur 2.0 SR2 instrument control (Thermo Scientific). Peptides were separated on a