[Defense] Investigating Persuasion Techniques in Social Engineering Cybercrime
Friday, November 8, 2024
3:30 pm - 4:30 pm
In
Partial
Fulfillment
of
the
Requirements
for
the
Degree
of
Doctor
of
Philosophy
Fatima
Zahra
Qachfar
will
defend
her
dissertation
Investigating
Persuasion
Techniques
in
Social
Engineering
Cybercrime
Abstract
Social engineering cybercrimes such as phishing and extortion pose significant security risks, where an attacker impersonates legitimate entities to obtain personal property by injecting malicious links or directly blackmailing victims. Despite advancements in machine learning for detecting phishing threats, the FBI’s Internet Crime Complaint Center (IC3) reported that phishing emails remain one of the top initial infection vectors used by attackers to target victims. To evade detection, attackers generate genuine-looking email attacks with the objective of convincing and persuading targets to take action by applying NLP persuasion techniques like ‘authority’, ‘scarcity’, and ‘consistency’. An attacker can use multiple persuasion strategies simultaneously to manipulate victims of different demographics and background knowledge into falling for persuasive phishing and extortion schemes. First, we examine user phishing susceptibility when facing persuasive phishing attacks. We then propose a multi-label detection system to detect persuasion and propaganda techniques used in phishing, hate speech and deception. Additionally, we examine different textual augmentation methods that can be used by attackers to craft deceptive phishing samples based on persuasion strategies.
Friday,
November
8,
2024
3:30
PM
-
4:30
PM
PGH 392
Dr. Rakesh Verma, dissertation advisor
Faculty, students, and the general public are invited.
