Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2507.16860

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

Apoorva Gulati·Rajesh Kumar·Vinti Agarwal·Aditya Sharma
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

cs.SIcs.CVcs.CY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Apoorva Gulati, Rajesh Kumar, Vinti Agarwal, Aditya Sharma. 2025-07-21. Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMs. https://arxiv.org/abs/2507.16860

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

User Influence Analysis Based on Blogs

Rumor and word of mouth spread at the same speed as the highway of information diffusion in the age of the internet. Social networks play quite an important role in the huge internet. Nowadays, social networks have become indispensable in our lives, especially for the government and enterprises. A social network becomes a complex information diffusion network with users working as nodes and the relationships between users working as the vehicle. In this paper, we propose three kinds of algorithms for computing user influence based on the behavior of a user's forwarding microblogs and the symbol of @ in microblogs. We evaluate the effectiveness of the algorithms by comparing the results of our work with the training data in the dataset, and in the end, it proves that our algorithms work well.

cs.SI↗
arXiv2026

Location transparency reduces activity by accounts misrepresenting their location on X

Concerns about inauthentic accounts, including foreign actors posing as domestic voices, are central to debates about online discourse. Yet, little is known about accounts with inaccurate location claims and how they behave when discrepancies between their claimed and actual locations become publicly visible. In November 2025, X introduced an "About this account" feature that discloses each account's platform-inferred location of operation. We leverage this intervention in a large-scale quasi-experimental study of 8,200 politically engaged accounts claiming a U.S. location, comparing accounts whose disclosed locations matched versus contradicted their claims across 1.3 million posts and 3.6 million replies over 21 weeks. Before disclosure, location-mismatched accounts posted more misleading, scam-related, and cryptocurrency-related content, but showed no distinctive partisan leaning. Difference-in-differences estimates show that disclosure reduced the posting activity of location-mismatched accounts by 13.1% with the largest declines among accounts revealed to be in Africa (29.2%) and Asia (24.4%), and among accounts with VPN flags, username changes, or scam- and crypto-heavy content. Additionally, the decline in their replies was concentrated in interactions with U.S.-based recipients (10.3%), whereas replies to non-U.S.-based recipients showed no statistically significant change. Conversely, there was no significant change in average audience engagement with their posts. Location transparency thus works primarily by inducing restraint among the disclosed accounts rather than by shifting audience behaviour, and the accounts it constrains look at least as much like cross-border fraud as foreign political influence.

cs.SI↗
arXiv2026

The Benefit of Collective Intelligence in Community-Based Content Moderation is Limited by Overt Political Signalling

Social media platforms face increasing scrutiny over the rapid spread of misinformation. In response, many have adopted community-based content moderation systems, including Community Notes (formerly Birdwatch) on X (formerly Twitter), Community Notes on Meta, and Footnotes on TikTok. However, research shows that the current design of these systems can allow political biases to influence both the development of notes and the rating processes, reducing their overall effectiveness. We hypothesise that enabling users to collaborate on writing notes, rather than relying solely on individually authored notes, can enhance the overall quality of their notes. To test this idea, we conducted an online experiment in which participants jointly authored notes on politically misleading posts. We find that collaboration improves the helpfulness of notes, although the average effect depends on the interactional context. In particular, the benefits of collaboration decline when participants are made aware of one another's political affiliations. We also find that politically diverse teams improve note quality when evaluating Republican posts, while team composition does not meaningfully affect note quality for Democrat posts. These findings underscore the complexity of community-based content moderation and highlight the importance of understanding group dynamics and political diversity when designing more effective moderation systems.

cs.SI↗