67 research outputs found
Recommended from our members
Machine Learning-based Author Identification for Social Media Forensics
No full textSocial media have gained extreme popularity due to the explosive growth of cyberinfrastructures, mobile devices, Internet technologies, and services. However, they also provide potential anonymity, which in turn harbors hacker forums, carding shops, underground marketplace, dark websites, and so on. As a result, social media have become the playground of cyber threat actors who conduct various malicious operations such as selling stolen cards, disseminating misinformation, propagating hacking tools, spreading malware samples, planning cyberattacks, and organizing trolling campaigns. Therefore, it is urgent to study effective methods that can identify the authors behind the digital text in order to enable forensic analysis, enhance security, and reduce social media misuse. In recent years, machine learning-based author identification has become a promising solution to identify the author of text. However, it is still an underexplored research field in social media forensics. This thesis investigates machine learning-based author identification subfields, including author attribution, author verification, author clustering, and their applications to social media forensics.
Internet Relay Chat (IRC) has traditionally been used for legitimate purposes. Yet, cyber threat actors extensively abuse it to generate a wide range of illegal content and perform malicious behaviors due to its potential anonymity and popularity among hackers. Unfortunately, author identification research in IRC remains a largely underexplored area. In this thesis, we first present our automatic social media monitoring and threat detection method that can effectively collect data for author identification tasks and then present a novel author attribution framework and its application to IRC. It consists of a holistic feature extraction model and an ensemble of ensembles for multi-class classification. We then bring a novel author verification framework under the principle of one-class learning to effectively verify the authorship of IRC texts.
This research also examines author clustering for social media forensics. Most author identification studies focus on author attribution and author verification, while the author clustering research is largely ignored. Meanwhile, cyber threat actors widely make use of Twitter to create alias accounts for numerous malicious purposes, especially in trolling campaigns and misinformation propagations. Thus, developing an effective author clustering method for Twitter is urgent. In this research, we developed a novel unsupervised learning-based author clustering framework and its application to Twitter. We delivered the capability to identify the group among many Twitter aliases even without prior knowledge of the number of authors.
We address the effectiveness and demonstrate the feasibility of our author identification frameworks through diverse experiments. Our author attribution approach can achieve more than 90% attribution accuracy given hundreds of candidates in the author attribution experiments. In the author verification experiments, over 70% of author cases, our author verification approach can achieve more than 99% AUC. In the author clustering experiments given more than one hundred unlabeled text samples, our author clustering approach attains an average accuracy of 81.93% when knowing the number of authors and an average accuracy of 74.78% without prior knowledge of the number of authors
Which Suture Material is Optimal for Pancreaticojejunostomy Anastomosis? An In Vitro Study
No full textBackground: Which suture material is optimal for pancreaticojejunostomy (PJ) anastomosis is a matter of debate with contradictory results. The aim of the present in vitro study was to determine the effects of pancreatic juice, bile, and their mixture on different suture materials in terms of breaking strength and disintegration. Material and Methods: Four suture materials, silk, polyglactin 910, polydioxanone, and polypropylene, were tested in pancreatic juice, bile, and their mixture. Determination of breaking strength and disintegration under electron microscope for each suture material was done on days 0, 3, 6, and 10. Results: The breaking strength of polyglactin 910 and silk was significantly higher than polypropylene and polydioxanone (p .05). No obvious disintegration has been observed under electron microscope in the architecture and appearance of suture materials after days of exposure to pancreatic juice, bile, and their mixture. Conclusions: None of the suture materials was disintegrated on exposure to pancreatic juice, bile, and their mixture. Polyglactin 910 has the highest breaking strength and significantly loses its strength throughout the experiment but still remains higher than other suture materials. Polypropylene, polydioxanone, and silk showed less variation across the incubation period
Surgical Outcomes of Solid Pseudopapillary Neoplasm of the Pancreas: A Single Institution's Experience of 16 Cases
No full textConclusion: SPT is a rare pancreatic neoplasm with a low malignant potential, and is common in young women. If SPT is diagnosed before surgery, complete surgical resection, generally enucleation is the most effective therapy for SPT
Extended transduodenal sphincteroplasty for bile duct stones associated with a periampullary diverticulum
No full textThe analysis of clinico-pathologic characteristics in patients who underwent surgery due to stricturing and non-perineal fistulizing forms of Crohn's disease: A retrospective cohort study
No full textConclusion: No specific clinical feature was found to differentiate patients with the stricturing form of Crohn's disease from the fistulizing form. However, histopathological analysis of the resected specimens revealed significant differences in some parameters between the two disease forms. (C) 2015 Surgical Associates Ltd. Published by Elsevier Ltd. All rights reserved
A Retrospective Analysis of Factors Affecting Early Stoma Complications
No full textDespite advances in surgical techniques and products for stoma care, stoma-related complications are still common. A retrospective analysis was performed of the medical records of 462 consecutive patients (295 [63.9%] female, 167 [36.1 %] male, mean age 55.5 +/- 15.1 years, mean body mass index [BMI] 25.1 +/- 5.2) who had undergone stoma creation at the Gastroenterological Surgery Clinic of Turkiye Yuksek Ihtisas Teaching and Research Hospital between January 2008 and December 2012 to examine the incidence of early (ie, within 30 days after surgery) stoma complications and identify potential risk factors. Variables abstracted included gender, age, and BMI; existence of malignant disease; comorbidities (diabetes mellitus, hypertension, coronary artery disease, chronic respiratory disease); use of neoadjuvant chemoradiotherapy; permanent or temporary stoma; type of stoma (loop/end stoma); stoma localization; and the use of preoperative marking of the stoma site. Data were entered and analyzed using statistical software. Descriptive statistics, chi-squared, and Mann-Whitney U tests were used to describe and analyze all variables, and logistic regression analysis was used to determine independent risk factors for stoma complications. Ostomy-related complications developed in 131 patients (28.4%) Of these, superficial mucocutaneous separation was the most frequent complication (90 patients, 19.5%), followed by stoma retraction (15 patients, 3.2%). In univariate analysis, malignant disease (P = .025), creation of a colostomy (P = .002), and left lower quadrant stoma location (P <. 001) were all significant indicators of stoma complication. Only stoma location was an independent risk factor for the development of a stoma complication (P = .044). The rate of stoma complications was not significantly different between patients who underwent nonemergent surgery (30% in patients preoperatively sited versus 28.4% not sited) and patients who underwent emergency surgery (27.1%). Early stoma complication rates were higher in patients with malignant diseases and with colostomies. The site of the stoma is an independent risk factor for the development of stoma complication. Preoperative marking for stoma creation should be considered to reduce the risk of stoma-related complications. Prospective, randomized controlled studies are needed to enhance understanding of the more prevalent risk factors
Successfully transplanted liver procured from a carbamate insecticide-poisoned donor: is acute intoxication an obstacle to organ retrieval?
No full textA case of primary (de novo) carcinoma of the uterine cervix after cadaveric orthotopic liver transplantation
No full textThe Rationality of Resectional Surgery and Palliative Interventions in the Management of Patients with Gallbladder Cancer
No full textThe aim of the present study was to evaluate in a retrospective manner, the survival period and survival rate according to stages and groups after R0, R1, R2 resections and palliative interventions. Between 2003 and 2012, 67 patients diagnosed with gallbladder carcinoma were retrospectively analyzed. Patient demographics, the survival period, and survival rate according to stages and groups after R0, R1, R2 resections and palliative interventions were retrospectively analyzed. Sixty-seven patients were diagnosed with gallbladder carcinoma. Thirty-eight patients (56.7%) were female and 29 patients (43.3%) were male. The median survival period was significantly longer in stage II and III diseases than in stage IV disease (P < 0.001). The R0, R1, and R2 resection rates in patients who underwent surgery with curative intent were 67.7, 19.4, and 12.9 per cent, respectively. The R0 resection rate according to the tumor stages was 100 per cent for stage I, 87.5 per cent for stage II, 66.7 per cent for stage III, and 42.8 per cent for stage IV disease. The median follow-up period was six months (eight days to 36 months). During this follow-up period, 53 patients (79.1%) died. In conclusion, R0 resection rate decreases when tumor stage increases. The highest survival rates after R0 resection are achieved in patients with stage I, II, and III diseases. Radical surgery has no benefit over palliative surgery for stage IV disease in terms of survival
AN ANOMALY BEHAVIOR ANALYSIS METHODOLOGY FOR NETWORK-CENTRIC SYSTEMS By
No full textRights Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author. Downloaded 3-Mar-2016 23:35:4
- …
