Intrusion detection under covariate shift using modified support vector machine and modified backpropagation

Cuong, Tran Dinh; Giang, Nguyen Linh

doi:10.1145/2350716.2350756

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Not surprisingly, such challenges and inequalities—sometimes compounded over time—can take a toll on women’s mental health and perceived control over their career and life trajectories (Kinman, 2001). While these mental health challenges (and gender disparities) are recognized at the graduate student level (Evans et al, 2018), support for postdoctoral fellows often falls through the cracks (Newsome, 2008). It is at this time—the pre-tenure track, postdoctoral stage when women are on the academic job market—that the pipeline appears to be at its leakiest (Martinez et al, 2007; Newsome, 2008; Goulden et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

A Leak in the Academic Pipeline: Identity and Health Among Postdoctoral Women

et al. 2019

View full text Add to dashboard Cite

Several challenges (e.g., sexism, parental leave, the glass ceiling, etc.) disproportionately affect women in academia (and beyond), and thus perpetuate the leaky pipeline metaphor for women who opt-out of an academic career. Although this pattern can be seen at all levels of the academic hierarchy, a critical time for women facing such challenges is during the postdoctoral stage, when personal life transitions and professional ambitions collide. Using a social identity approach, we explore factors affecting the mental health of postdoctoral women, including identity development (e.g., as a mother, a scientist) and lack of control (uncertainty about one’s future personal and professional prospects), which likely contribute to the leak from academia. In this mixed-method research, Study 1 comprised interviews with postdoctoral women in North America ( n = 13) and Europe ( n = 8) across a range disciplines (e.g., psychology, physics, political science). Common themes included the negative impact of career uncertainty, gender-based challenges (especially sexism and maternity leave), and work-life balance on mental and physical health. However, interviewees also described attempts to overcome gender inequality and institutional barriers by drawing on support networks. Study 2 comprised an online survey of postdoctoral women ( N = 146) from a range of countries and academic disciplines to assess the relationships between social identification (e.g., disciplinary, gender, social group), perceived control (i.e., over work and life), and mental health (i.e., depression, anxiety, stress, and life satisfaction). Postdoctoral women showed mild levels of stress and depression, and were only slightly satisfied with life. They also showed only moderate levels of perceived control over one’s life and work. However, hierarchical regression analyses revealed that strongly identifying with one’s discipline was most consistently positively associated with both perceived control and mental health. Collectively, these findings implicate the postdoctoral stage as being stressful and tenuous for women regardless of academic background or nationality. They also highlight the importance of disciplinary identity as a potentially protective factor for mental health that, in turn, may diminish the rate at which postdoctoral women leak from the academic pipeline.

show abstract

Section: Introductionmentioning

confidence: 99%

A Leak in the Academic Pipeline: Identity and Health Among Postdoctoral Women

et al. 2019

View full text Add to dashboard Cite

show abstract

Intrusion Detection Systems Using Support Vector Machines on the KDDCUP’99 and NSL-KDD Datasets: A Comprehensive Survey

Ngueajio

Washington²,

Rawat³

et al. 2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

With the growing rates of cyber-attacks and cyber espionage, the need for better and more powerful intrusion detection systems (IDS) is even more warranted nowadays. The basic task of an IDS is to act as the first line of defense, in detecting attacks on the internet. As intrusion tactics from intruders become more sophisticated and difficult to detect, researchers have started to apply novel Machine Learning (ML) techniques to effectively detect intruders and hence preserve internet users' information and overall trust in the entire internet network security. Over the last decade, there has been an explosion of research on intrusion detection techniques based on ML and Deep Learning (DL) architectures on various cyber security-based datasets such as the DARPA, KDDCUP'99, NSL-KDD, CAIDA, CTU-13, UNSW-NB15. In this research, we review contemporary literature and provide a comprehensive survey of different types of intrusion detection technique that applies Support Vector Machines (SVMs) algorithms as a classifier. We focus only on studies that have been evaluated on the two most widely used datasets in cybersecurity namely: the KDDCUP'99 and the NSL-KDD datasets. We provide a summary of each method, identifying the role of the SVMs classifier, and all other algorithms involved in the studies. Furthermore, we present a critical review of each method, in tabular form, highlighting the performances measures, strengths, and limitations, of each of the methods surveyed.

show abstract

Analysis of Support Vector Machine-based Intrusion Detection Techniques

Bhati

2019

Arab J Sci Eng

View full text Add to dashboard Cite

Intrusion detection under covariate shift using modified support vector machine and modified backpropagation

Cited by 3 publications

References 8 publications

A Leak in the Academic Pipeline: Identity and Health Among Postdoctoral Women

A Leak in the Academic Pipeline: Identity and Health Among Postdoctoral Women

Intrusion Detection Systems Using Support Vector Machines on the KDDCUP’99 and NSL-KDD Datasets: A Comprehensive Survey

Analysis of Support Vector Machine-based Intrusion Detection Techniques

Contact Info

Product

Resources

About