41 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
Elevated Plasma Levels of PAI-1 Predict Cardiovascular Events and Cardiovascular Mortality in Prevalent Peritoneal Dialysis Patients
No full textBackground. Elevated plasminogen activator inhibitor-1 (PAI-1) levels are associated with increased cardiovascular (CV) risk in the general population. It has been shown that peritoneal dialysis (PD) patients have increased plasma levels of PAI-1. The aim of this study was to investigate whether PAI-1 independently predicted CV outcome in PD patients. Material and Methods. Seventy-two PD patients (53% females, mean age 49.9 +/- 16.1 years) were studied. Twelve patients who underwent kidney transplantation and 14 patients who transferred to hemodialysis during follow-up were excluded from the analysis. The remaining 46 patients (54% female, mean age 54 +/- 16 years, dialytic age 42 +/- 30 months) were followed a mean time of 45.4 +/- 19.4 months (range 8-71 months). Baseline PAI-1, clinical, and laboratory parameters were assessed in all patients. Survival analyses were made with Kaplan-Meier and Cox regression analysis, with all-cause mortality and CV mortality and CV events (CVEs) as clinical end points. Results. During the follow-up, 29 patients died (17 from CV causes), and 28 fatal and non-fatal CVEs were recorded. The patients were divided according to plasma PAI-1 levels (i.e., <= or >41 ng/mL). The significant independent predictors of all-cause of mortality were age (>60 years; p = 0.018), CRP (>5 mg/L; p = 0.015), and serum albumin (<3.5 g/L; p = 0.011). Multivariable Cox regression analysis showed that plasma PAI-1 >41 ng/mL was independently predictive of higher CV mortality (p = 0.021) and CVEs (p = 0.001). The only other independent predictor of CV mortality was only CRP (>5 mg/L; p = 0.008). Conclusions. Plasma levels of PAI-1 >41 ng/mL is a significant predictor of CV mortality and CVEs in PD patients
The blockade of the renin-angiotensin system reverses tacrolimus related cardiovascular toxicity at the histopathological level
No full textIntroduction. In this study, we investigate the toxic effects of tacrolimus (FK506) on the cardiovascular system at the histopathological level in a rat model and whether these effects can be reversed by the blockade of the renin-angiotensin system (RAS) by either an angiotensin-converting enzyme inhibitor (ACE-inhibitors) or an angiotensin receptor antagonist (ARB). Methods and results. Thirty-one Wistar rats were divided into four groups. FK506 group was treated with FK506 intraperitoneally (i.p.), FK506+ACE-inhibitors and FK506+ARB groups were treated with either quinapril or valsartan orally in addition to FK506. Control group was treated with saline i.p. Histological and immunohistochemical staining of cardiovascular tissue in the FK506 group showed increased vacuolar degeneration (11.2 vs. 5.8, p=0.008), arterial hyalinosis (10.7 vs. 6.3, p=0.036), transforming growth factor-beta (TGF-P) (12.2 vs. 4.8, p=0.001) and vascular endothelial growth factor expression (VEGF) (10.7 vs. 6.3, p=0.036), elastic van Gieson (11.5 vs. 5.5, p=0.004), and periodic acid Schiff stain scores (12.5 vs. 4.5, p < 0.001) compared to the control group. Immunoihistochemical scores showed that expression of TGF-P is up-regulated, and bone morphogenic protein (BMP-7) is down-regulated with FK506 toxicity.Adding RAS blockade with either an ACE-inhibitor or an ARB could reverse FK506 induced changes. Both FK506+ACE-inhibitors and FK506+ARB groups demonstrated decrease in arterial hyalinosis (22.1 vs. 14.4 (FK5o6+ACE-inhibitor) and 13.6 (FK506+ARB), p=0.09) and vacuolar degeneration (23.1 vs. 16.1 (FK506+ACEinhibitor) and 12.4 (FK506+ARB), p=0.006) scores compared to the FK506 group. Conclusion. Blockade of RAS could reverse the histopathological signs of FK506 induced cardiac toxicity in a rat model
The effect of leucotrien antagonists on peritoneal functional and morphological changes induced by hypertonic solutions in an experimental model of CAPD in rats
No full text
Paraoxonase 1 Polymorphisms in Patients With Primary Glomerulonephritis A Single-center Study in Turkey
No full textIntroduction. Human paraoxonase 1 (PON1) is an enzyme related with high-density lipoprotein cholesterol. The link between genetic polymorphisms of PON1 and hyperlipidemia and increased lipid oxidation may explain these complications in the course of glomerular diseases. In this study, we aimed to investigate PON1 192 and PON1 55 polymorphisms in patients with primary glomerulonephritis and healthy individuals. Materials and Methods. Eighty-six patients with biopsy-proven primary glomerulonephritis and 50 healthy controls were included in the study. Clinical characteristics, lipid profile, paraoxonase activity, and PON1 genotypes (PON1 192 and PON1 55) of all of the participants were studied. Results. Histopathological diagnoses of the patients were membranoproliferative glomerulonephritis (53.5%), focal segmental glomerulosclerosis (33.7%), and membranous nephropathy (12.8%). The patients had lower PON1 activity levels than the healthy controls. No differences were observed in PON1 192 genotypes between the two groups. However, the controls were more likely to carry PON1 55 LM genotype (odds ratio, 4.10; 95% confidence interval, 1.96 to 8.61; P <.001) and M allele (odds ratio, 3.0; 95% confidence interval, 1.45 to 6.19; P =.003) compared to the patients with primary glomerulonephritis. There was a marked elevation in the frequency of PON1 55 LL genotype in the patients compared to the controls (odds ratio, 0.33; 95% confidence interval, 0.16 to 0.68; P =.003). Conclusions. This preliminary study shows that the LL genotype might be a risk factor for the development of primary glomerulonephritis and the M allele might be a protective factor against its progression
Associations between apolipoprotein E gene polymorphism and plasminogen activator inhibitor-1 and atherogenic lipid profile in dialysis patients
No full textBackground. Apolipoprotein-E (ApoE) gene polymorphism has an important role in lipoprotein metabolism and could participate in the development of cardiovascular diseases (CVD). Plasminogen activator inhibitor-1 (PAI-1) is also regarded as a risk factor for CVD. The aim of the present study is to further investigate the possible link(s) between ApoE gene polymorphism and plasma PAI-1 antigen and serum lipid profile in peritoneal dialysis (PD) and hemodialysis (HD) patients. Material and Methods. We studied 72 PD patients (38 female, mean age 49.9 +/- 16.1 years), 72 HD patients (22 female, mean age 57.4 +/- 14.6 years), and 42 healthy subjects (21 female, mean age 50.1 +/- 18.6 years). Serum lipid parameters, plasma PAI-1 levels, and ApoE genotypes were determined in all subjects. Results. The distribution of ApoE genotypes and alleles frequencies was similar in dialysis patients and healthy controls. In PD patients, total cholesterol (TC), low-density lipoprotein (LDL)-C, and ApoB levels were significantly higher than that of HD patients. HD patients with E3/4 genotype had elevated TC, LDL-C and ApoB levels compared with E3/3 genotype. TC and triglyceride levels were also higher in E3/4 genotype than that of E2/3 genotype. PD and HD patients showed a significantly increased PAI-1 level s compared with controls, whereas PAI-1 levels were highest in HD patients. There was no significant relation between ApoE genotypes and PAI-1 levels. Conclusions. The present study suggests that ApoE polymorphism significantly affects serum lipid profile in HD patients and epsilon 4 allele carriers are more susceptible to have atherogenic lipid profile
Paraoxonase 1 polymorphisms in patients with primary glomerulonephritis: a single-center study in Turkey
No full textINTRODUCTION: Human paraoxonase 1 (PON1) is an enzyme related with high-density lipoprotein cholesterol. The link between genetic polymorphisms of PON1 and hyperlipidemia and increased lipid oxidation may explain these complications in the course of glomerular diseases. In this study, we aimed to investigate PON1 192 and PON1 55 polymorphisms in patients with primary glomerulonephritis and healthy individuals. MATERIALS AND METHODS: Eighty-six patients with biopsy-proven primary glomerulonephritis and 50 healthy controls were included in the study. Clinical characteristics, lipid profile, paraoxonase activity, and PON1 genotypes (PON1 192 and PON1 55) of all of the participants were studied. RESULTS: Histopathological diagnoses of the patients were membranoproliferative glomerulonephritis (53.5%), focal segmental glomerulosclerosis (33.7%), and membranous nephropathy (12.8%). The patients had lower PON1 activity levels than the healthy controls. No differences were observed in PON1 192 genotypes between the two groups. However, the controls were more likely to carry PON1 55 LM genotype (odds ratio, 4.10; 95% confidence interval, 1.96 to 8.61; P < .001) and M allele (odds ratio, 3.0; 95% confidence interval, 1.45 to 6.19; P = .003) compared to the patients with primary glomerulonephritis. There was a marked elevation in the frequency of PON1 55 LL genotype in the patients compared to the controls (odds ratio, 0.33; 95% confidence interval, 0.16 to 0.68; P = .003). CONCLUSIONS: This preliminary study shows that the LL genotype might be a risk factor for the development of primary glomerulonephritis and the M allele might be a protective factor against its progression
