mlsanityData to 14 Oct 2026

Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMs

arXiv 2507.16860 ↗First posted 21 Jul 2025cs.SI cs.CV cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have made it easier to create realistic fake profiles on platforms like LinkedIn. This poses a significant risk for text-based fake profile detectors. In this study, we evaluate the robustness of existing detectors against LLM-generated profiles. While highly effective in detecting manually created fake profiles (False Accept Rate: 6-7%), the existing detectors fail to identify GPT-generated profiles (False Accept Rate: 42-52%). We propose GPT-assisted adversarial training as a countermeasure, restoring the False Accept Rate to between 1-7% without impacting the False Reject Rates (0.5-2%). Ablation studies revealed that detectors trained on combined numerical and textual embeddings exhibit the highest robustness, followed by those using numerical-only embeddings, and lastly those using textual-only embeddings. Complementary analysis on the ability of prompt-based GPT-4Turbo and human evaluators affirms the need for robust automated detectors such as the one proposed in this study.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

16 of 32 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  5. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
  6. 2017Enhancing Robustness of Machine Learning Systems via Data Transformationscited by 38
  7. 2020Improving Calibration through the Relationship with Adversarial Robustnesscited by 26
  8. 2025Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)cited by 20
  9. 2020Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networkscited by 19
  10. 2023The Looming Threat of Fake and LLM-generated LinkedIn Profiles: Challenges and Opportunities for Detection and Preventioncited by 18
  11. 2013SybilBelief: A Semi-supervised Learning Approach for Structure-based Sybil Detectioncited by 11
  12. 2024Keystroke Dynamics Against Academic Dishonesty in the Age of LLMscited by 6
4 more
  1. 2024Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifierscited by 6
  2. 2024Towards Certification of Uncertainty Calibration under Adversarial Attackscited by 5
  3. 2023Spotting Fake Profiles in Social Networks via Keystroke Dynamicscited by 3
  4. 2020Identifying Fake Profiles in LinkedIncited by 2

Built on by

Not cited yet.