# Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges

arXiv: https://arxiv.org/abs/2403.18249 · HTML: https://mlsanity.com/paper/2403.18249/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [On the Risk of Misinformation Pollution with Large Language Models](https://mlsanity.com/paper/2305.13661/) (2023)
- [DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning](https://mlsanity.com/paper/1809.06416/) (2018)
- [Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks](https://mlsanity.com/paper/2310.10830/) (2023)
- [Contrasting Linguistic Patterns in Human and LLM-Generated News Text](https://mlsanity.com/paper/2308.09067/) (2023)
- [Exploring Adversarial Examples in Malware Detection](https://mlsanity.com/paper/1810.08280/) (2018)
- [Disinformation Detection: An Evolving Challenge in the Age of LLMs](https://mlsanity.com/paper/2309.15847/) (2023)
- [Disinformation Capabilities of Large Language Models](https://mlsanity.com/paper/2311.08838/) (2023)
- [Adapting Fake News Detection to the Era of Large Language Models](https://mlsanity.com/paper/2311.04917/) (2023)
- [Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT](https://mlsanity.com/paper/2306.07401/) (2023)
- [Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing](https://mlsanity.com/paper/2304.02017/) (2023)
- [Med-MMHL: A Multi-Modal Dataset for Detecting Human- and LLM-Generated Misinformation in the Medical Domain](https://mlsanity.com/paper/2306.08871/) (2023)

## Built on by (most cited first, 30 of 30)

- [Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks](https://mlsanity.com/paper/2409.08087/) (2024)
- [Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey](https://mlsanity.com/paper/2409.11564/) (2024)
- [Generative Monoculture in Large Language Models](https://mlsanity.com/paper/2407.02209/) (2024)
- [LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation](https://mlsanity.com/paper/2504.20013/) (2025)
- [The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making](https://mlsanity.com/paper/2410.07304/) (2024)
- [Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models](https://mlsanity.com/paper/2411.11496/) (2024)
- [RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking](https://mlsanity.com/paper/2506.12538/) (2025)
- [MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models](https://mlsanity.com/paper/2408.11871/) (2024)
- [Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors](https://mlsanity.com/paper/2410.19230/) (2024)
- [JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks](https://mlsanity.com/paper/2603.01291/) (2026)
- [Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Models](https://mlsanity.com/paper/2406.17992/) (2024)
- [Large Language Models can impersonate politicians and other public figures](https://mlsanity.com/paper/2407.12855/) (2024)
- [Seeing Through AI's Lens: Enhancing Human Skepticism Towards LLM-Generated Fake News](https://mlsanity.com/paper/2406.14012/) (2024)
- [Adversarial Attacks against Neural Ranking Models via In-Context Learning](https://mlsanity.com/paper/2508.15283/) (2025)
- [The Compositional Architecture of Regret in Large Language Models](https://mlsanity.com/paper/2506.15617/) (2025)
- [Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection](https://mlsanity.com/paper/2508.12632/) (2025)
- [A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection](https://mlsanity.com/paper/2508.19633/) (2025)
- [Model Attribution in LLM-Generated Disinformation: A Domain Generalization Approach with Supervised Contrastive Learning](https://mlsanity.com/paper/2407.21264/) (2024)
- [LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection](https://mlsanity.com/paper/2604.04815/) (2026)
- [Passing the Turing Test in Political Discourse: Fine-Tuning LLMs to Mimic Polarized Social Media Comments](https://mlsanity.com/paper/2506.14645/) (2025)
- [An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs](https://mlsanity.com/paper/2508.10010/) (2025)
- [VOW: Verifiable and Oblivious Watermark Detection for Large Language Models](https://mlsanity.com/paper/2604.27666/) (2026)
- [Auction-Based Regulation for Artificial Intelligence](https://mlsanity.com/paper/2410.01871/) (2024)
- [Truth in Text: A Meta-Analysis of ML-Based Cyber Information Influence Detection Approaches](https://mlsanity.com/paper/2503.22686/) (2025)
- [Synthetic News Generation for Fake News Classification](https://mlsanity.com/paper/2503.24206/) (2025)
- [Artificial Intelligence / Human Intelligence: Who Controls Whom?](https://mlsanity.com/paper/2512.04131/) (2025)
- [A Causal Perspective for Enhancing Jailbreak Attack and Defense](https://mlsanity.com/paper/2602.04893/) (2026)
- [Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs](https://mlsanity.com/paper/2603.21155/) (2026)
- [Exploring and Developing a Pre-Model Safeguard with Draft Models](https://mlsanity.com/paper/2605.19321/) (2026)
- [Let the Bullets Fly: Multimodal Fake News Detection with Temporal-Aligned Generative Danmaku](https://mlsanity.com/paper/2608.22832/) (2026)

## Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have enabled the creation of fake news, particularly in complex fields like healthcare. Studies highlight the gap in the deceptive power of LLM-generated fake news with and without human assistance, yet the potential of prompting techniques has not been fully explored. Thus, this work aims to determine whether prompting strategies can effectively narrow this gap. Current LLM-based fake news attacks require human intervention for information gathering and often miss details and fail to maintain context consistency. Therefore, to better understand threat tactics, we propose a strong fake news attack method called conditional Variational-autoencoder-Like Prompt (VLPrompt). Unlike current methods, VLPrompt eliminates the need for additional data collection while maintaining contextual coherence and preserving the intricacies of the original text. To propel future research on detecting VLPrompt attacks, we created a new dataset named VLPrompt fake news (VLPFN) containing real and fake texts. Our experiments, including various detection methods and novel human study metrics, were conducted to assess their performance on our dataset, yielding numerous findings.