Overconfidence in Phishing Email Detection

被引:51
|
作者
Wang, Jingguo [1 ]
Li, Yuan [2 ]
Rao, H. Raghav [3 ]
机构
[1] Univ Texas Arlington, Coll Business, Informat Syst & Operat Management, Arlington, TX 76019 USA
[2] Columbia Coll, Business Math & Sci, Columbia, MO USA
[3] Univ Texas San Antonio, Coll Business, Informat Syst & Cyber Secur, San Antonio, TX USA
来源
基金
美国国家科学基金会;
关键词
Phishing Email Detection; Overconfidence; Judgmental Bias; Judgmental Confidence; Judgmental Accuracy; Phishing Detection Self-efficacy; Cognitive Strategies; Motivational Factors; PROBABILITY JUDGMENTS; INFORMATION SEARCH; COGNITIVE EFFORT; SELF-EFFICACY; CONFIDENCE; CALIBRATION; ACCURACY; BEHAVIOR; RESOLUTION; KNOWLEDGE;
D O I
10.17705/1jais.00442
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This study examines overconfidence in phishing email detection. Researchers believe that overconfidence (i.e., where one's judgmental confidence exceeds one's actual performance in decision making) can lead to one's adopting risky behavior in uncertain situations. This study focuses on what leads to overconfidence in phishing detection. We performed a survey experiment with 600 subjects to collect empirical data for the study. In the experiment, each subject judged a set of randomly selected phishing emails and authentic business emails. Specifically, we examined two metrics of overconfidence (i.e., overprecision and overestimation). Results show that cognitive effort decreased overconfidence, while variability in attention allocation, dispositional optimism, and familiarity with the business entities in the emails all increased overconfidence in phishing email detection. The effect of perceived self-efficacy of detecting phishing emails on overconfidence was marginal. In addition, all confidence beliefs poorly predicted detection accuracy and poorly explained its variance, which highlights the issue of relying on them to guide one's behavior in detecting phishing. We discuss mechanisms to reduce overconfidence.
引用
收藏
页码:759 / 783
页数:25
相关论文
共 50 条
  • [31] Leveraging Synthetic Data and PU Learning For Phishing Email Detection
    Qachfar, Fatima Zahra
    Verma, Rakesh M.
    Mukherjee, Arjun
    CODASPY'22: PROCEEDINGS OF THE TWELVETH ACM CONFERENCE ON DATA AND APPLICATION SECURITY AND PRIVACY, 2022, : 29 - 40
  • [32] Semantic Feature Selection for Text with Application to Phishing Email Detection
    Verma, Rakesh
    Hossain, Nabil
    INFORMATION SECURITY AND CRYPTOLOGY - ICISC 2013, 2014, 8565 : 455 - 468
  • [33] Enhancing Phishing Email Detection through Ensemble Learning and Undersampling
    Qi, Qinglin
    Wang, Zhan
    Xu, Yijia
    Fang, Yong
    Wang, Changhui
    APPLIED SCIENCES-BASEL, 2023, 13 (15):
  • [34] Towards Enhanced Security: An improved approach to Phishing Email Detection
    Sambare, G. B.
    Galande, Shailesh B.
    Kale, Sharvari
    Nehete, Pragati
    Jadhav, Vaishnavi
    Tadavi, Nihal
    JOURNAL OF ELECTRICAL SYSTEMS, 2024, 20 (02) : 2763 - 2772
  • [35] Phishing Email Detection Based on Binary Search Feature Selection
    Sonowal G.
    SN Computer Science, 2020, 1 (4)
  • [36] A Systematic Review of Deep Learning Techniques for Phishing Email Detection
    Kyaw, Phyo Htet
    Gutierrez, Jairo
    Ghobakhlou, Akbar
    ELECTRONICS, 2024, 13 (19)
  • [37] Fighting Phishing with Trusted Email
    Crain, Jordan
    Opyrchal, Lukasz
    Prakash, Atul
    FIFTH INTERNATIONAL CONFERENCE ON AVAILABILITY, RELIABILITY, AND SECURITY: ARES 2010, PROCEEDINGS, 2010, : 462 - 467
  • [38] A comprehensive dual-layer architecture for phishing and spam email detection
    Doshi, Jay
    Parmar, Kunal
    Sanghavi, Raj
    Shekokar, Narendra
    COMPUTERS & SECURITY, 2023, 133
  • [39] Advancing Phishing Email Detection: A Comparative Study of Deep Learning Models
    Altwaijry, Najwa
    Al-Turaiki, Isra
    Alotaibi, Reem
    Alakeel, Fatimah
    SENSORS, 2024, 24 (07)
  • [40] Using Feature Selection and Classification Scheme for Automating Phishing Email Detection
    Hamid, Isredza Rahmi A.
    Abawajy, Jemal
    Kim, Tai-hoon
    STUDIES IN INFORMATICS AND CONTROL, 2013, 22 (01): : 61 - 70