# Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation

arXiv: https://arxiv.org/abs/2412.13666 · HTML: https://mlsanity.com/paper/2412.13666/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 11 of 11)

- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [A Categorical Archive of ChatGPT Failures](https://mlsanity.com/paper/2302.03494/) (2023)
- [Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations](https://mlsanity.com/paper/2301.04246/) (2023)
- [MAGE: Machine-generated Text Detection in the Wild](https://mlsanity.com/paper/2305.13242/) (2023)
- [GRUEN for Evaluating Linguistic Quality of Generated Text](https://mlsanity.com/paper/2010.02498/) (2020)
- [METAL: Towards Multilingual Meta-Evaluation](https://mlsanity.com/paper/2404.01667/) (2024)
- [Large language models can consistently generate high-quality content for election disinformation operations](https://mlsanity.com/paper/2408.06731/) (2024)
- [IMGTB: A Framework for Machine-Generated Text Detection Benchmarking](https://mlsanity.com/paper/2311.12574/) (2023)
- [KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection](https://mlsanity.com/paper/2402.13671/) (2024)
- [Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims](https://mlsanity.com/paper/2402.08467/) (2024)

## Built on by (most cited first, 20 of 20)

- [Security Concerns for Large Language Models: A Survey](https://mlsanity.com/paper/2505.18889/) (2025)
- [ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents](https://mlsanity.com/paper/2603.12614/) (2026)
- [Authorship Attribution in Multilingual Machine-Generated Texts](https://mlsanity.com/paper/2508.01656/) (2025)
- [mdok of KInIT: Robustly Fine-tuned LLM for Binary and Multiclass AI-Generated Text Detection](https://mlsanity.com/paper/2506.01702/) (2025)
- [Adversarial Attacks against Neural Ranking Models via In-Context Learning](https://mlsanity.com/paper/2508.15283/) (2025)
- [The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence](https://mlsanity.com/paper/2601.05478/) (2026)
- [Tailored untruths: How personalisation challenges LLM safeguards](https://mlsanity.com/paper/2510.12993/) (2025)
- [Retrieving Climate Change Disinformation by Narrative](https://mlsanity.com/paper/2603.22015/) (2026)
- [Beyond speculation: Measuring the growing presence of LLM-generated texts in multilingual disinformation](https://mlsanity.com/paper/2503.23242/) (2025)
- [ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety](https://mlsanity.com/paper/2508.20468/) (2025)
- [PerQ: Efficient Evaluation of Multilingual Text Personalization Quality](https://mlsanity.com/paper/2509.25903/) (2025)
- [WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking](https://mlsanity.com/paper/2512.00837/) (2025)
- [Evaluation of Multilingual LLMs Personalized Text Generation Capabilities Targeting Groups and Social-Media Platforms](https://mlsanity.com/paper/2601.03752/) (2026)
- [ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation](https://mlsanity.com/paper/2601.12983/) (2026)
- [Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts](https://mlsanity.com/paper/2605.12890/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)
- [Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeech](https://mlsanity.com/paper/2607.26236/) (2026)
- [Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts](https://mlsanity.com/paper/2608.09510/) (2026)
- [VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation](https://mlsanity.com/paper/2609.35028/) (2026)
- [Can Multimodal Large Language Models Generate and Detect Multimodal Social Media Fake News?](https://mlsanity.com/paper/2609.35809/) (2026)

## Abstract (arXiv)

The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be effectively misused for generating disinformation news articles following predefined narratives. Their capabilities to generate personalized (in various aspects) content have also been evaluated and mostly found usable. However, a combination of personalization and disinformation abilities of LLMs has not been comprehensively studied yet. Such a dangerous combination should trigger integrated safety filters of the LLMs, if there are some. This study fills this gap by evaluating vulnerabilities of recent open and closed LLMs, and their willingness to generate personalized disinformation news articles in English. We further explore whether the LLMs can reliably meta-evaluate the personalization quality and whether the personalization affects the generated-texts detectability. Our results demonstrate the need for stronger safety-filters and disclaimers, as those are not properly functioning in most of the evaluated LLMs. Additionally, our study revealed that the personalization actually reduces the safety-filter activations; thus effectively functioning as a jailbreak. Such behavior must be urgently addressed by LLM developers and service providers.