Online Social Deception and Its Countermeasures for Trustworthy Cyberspace: A Survey

Zhen Guo, Jin-Hee Cho, Ing-Ray Chen, Srijan Sengupta, Michin Hong, Tanushree MitraarXiv 2020 · DOI · OpenReview

Abstract

We are living in an era when online communication over social network services (SNSs) have become an indispensable part of people's everyday lives. As a consequence, online social deception (OSD) in SNSs has emerged as a serious threat in cyberspace, particularly for users vulnerable to such cyberattacks. Cyber attackers have exploited the sophisticated features of SNSs to carry out harmful OSD activities, such as financial fraud, privacy threat, or sexual/labor exploitation. Therefore, it is critical to understand OSD and develop effective countermeasures against OSD for building a trustworthy SNSs. In this paper, we conducted an extensive survey, covering (i) the multidisciplinary concepts of social deception; (ii) types of OSD attacks and their unique characteristics compared to other social network attacks and cybercrimes; (iii) comprehensive defense mechanisms embracing prevention, detection, and response (or mitigation) against OSD attacks along with their pros and cons; (iv) datasets/metrics used for validation and verification; and (v) legal and ethical concerns related to OSD research. Based on this survey, we provide insights into the effectiveness of countermeasures and the lessons from existing literature. We conclude this survey paper with an in-depth discussions on the limitations of the state-of-the-art and recommend future research directions in this area.

Introduction

As social network services (SNSs) have integrated into the fabric of daily life, they have simultaneously become a fertile breeding ground for deception. While traditional cybersecurity focuses on software vulnerabilities, Online Social Deception (OSD) targets the human element. It is a unique class of cyberattack because it requires the "cooperation" of the victim—the deceivee must believe the lie for the attack to succeed. This paper addresses the lack of a holistic, system-level understanding of OSD by bridging the gap between technical cybercrime research and social network threat analysis.

Multidisciplinary Conceptualization

Deception in cyberspace is not merely a technical anomaly; it is a complex human behavior rooted in diverse academic traditions. To build effective countermeasures, researchers must look beyond computer science to understand the psychological and sociological cues that define deceptive intent.

Multidisciplinary concepts of deception

As illustrated in Figure 2, the framework for OSD draws from philosophy (misleading to form false beliefs), psychology (introducing false beliefs), and linguistics (verbal communication as a tool). These fields provide "deception cues," such as increased cognitive load or specific linguistic patterns, which are essential for developing sophisticated detection algorithms.

The survey categorizes OSD into five major attack vectors, each with distinct characteristics and varying levels of academic coverage:

  1. False Information: Misinformation, rumors, and fake news.
  2. Luring: Phishing and spamming.
  3. Fake Identity: Sybil attacks, profile cloning, and compromised accounts.
  4. Crowdturfing: Coordinated efforts by paid workers to spread malicious content.
  5. Human Targeted Attacks: Cyberbullying, stalking, and trafficking.
Research distribution across OSD attack categories

Figure 5 highlights the current research landscape. While "False Information" (particularly fake news) and "Luring" (spamming) have received significant attention, there is a glaring shortage of research into sensitive "Human Targeted Attacks" like trafficking and grooming. This gap is largely due to the ethical and privacy constraints involved in collecting real-world datasets for these specific crimes.

Defense Framework Analysis

The paper evaluates defense mechanisms across three critical stages of the attack lifecycle:

  • Prevention: Proactive strategies include the use of "social honeypots"—fake accounts created by defenders to trap attackers and harvest their profiles before they reach legitimate users. Data-driven whitelists also play a role in early-stage defense.
  • Detection: This is the most mature area of research, dominated by supervised machine learning (e.g., SVM, Random Forest, Deep Learning). Effective detection often requires a hybrid approach, combining user profile metadata, linguistic features (NLP), and network structure analysis (using epidemic models like SIR or SEIZ).
  • Response and Mitigation: This remains the least explored stage. It involves strategies for account restoration and limiting the spread of misinformation once it has been identified.

Key Insights and Results

  • The Spectrum of Deception: Deception is not always malicious; it can include benign "white lies" or self-protection. Technical tools must distinguish intent to avoid high false-positive rates.
  • Linguistic Cues: Deceptive communication often exhibits identifiable markers, such as fewer first-person singular pronouns and a higher frequency of "sense-based" words (e.g., seeing, touching) used to fabricate a sense of reality.
  • Network Dynamics: False information often spreads faster than truth. Epidemic models like SEIZ (Susceptible, Exposed, Infected, Skeptic) are particularly effective at capturing the unique "exposure delay" characteristic of rumors.

Limitations and Future Directions

Despite advancements, several challenges remain. Most current OSD tools are "culture-blind," developed primarily for Western contexts, whereas deception cues are often culturally sensitive. Furthermore, the "privacy-security tradeoff" complicates the collection of granular data needed for subtle detection. Finally, the rise of Adversarial Machine Learning (AML) allows attackers to build bots that mimic human behavior more closely, necessitating a continuous evolution of defensive strategies.

Summary updated

Abstract

We are living in an era when online communication over social network services (SNSs) have become an indispensable part of people's everyday lives. As a consequence, online social deception (OSD) in SNSs has emerged as a serious threat in cyberspace, particularly for users vulnerable to such cyberattacks. Cyber attackers have exploited the sophisticated features of SNSs to carry out harmful OSD activities, such as financial fraud, privacy threat, or sexual/labor exploitation. Therefore, it is critical to understand OSD and develop effective countermeasures against OSD for building a trustworthy SNSs. In this paper, we conducted an extensive survey, covering (i) the multidisciplinary concepts of social deception; (ii) types of OSD attacks and their unique characteristics compared to other social network attacks and cybercrimes; (iii) comprehensive defense mechanisms embracing prevention, detection, and response (or mitigation) against OSD attacks along with their pros and cons; (iv) datasets/metrics used for validation and verification; and (v) legal and ethical concerns related to OSD research. Based on this survey, we provide insights into the effectiveness of countermeasures and the lessons from existing literature. We conclude this survey paper with an in-depth discussions on the limitations of the state-of-the-art and recommend future research directions in this area.
BibTeX
@misc{guo2020online,
  author = {Zhen Guo and Jin-Hee Cho and Ing-Ray Chen and Srijan Sengupta and Michin Hong and Tanushree Mitra},
  title = {{Online Social Deception and Its Countermeasures for Trustworthy Cyberspace: A Survey}},
  year = {2020},
  eprint = {2004.07678},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2004.07678},
}
Figure