{"ID":2892380,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16860","arxiv_id":"2507.16860","title":"Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMs","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.16860","url_pdf":"https://arxiv.org/pdf/2507.16860v1","authors":"[\"Apoorva Gulati\",\"Rajesh Kumar\",\"Vinti Agarwal\",\"Aditya Sharma\"]","published":"2025-07-21T17:23:52Z","proceeding":"cs.SI","tasks":"[\"cs.SI\",\"cs.CV\",\"cs.CY\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}