Skip to main content
LLM Security Database
Skip to research details
Back to research findings
LMVD-ID: 82d129c7
Paper published March 1, 2024
Entry analyzed March 4, 2025
Paper-reported evidence
Confidence: Source-linked

The LMVD-ID is an internal research identifier, not an official CVE identifier.

LLM Fake News Generation

Large Language Models (LLMs) are vulnerable to a novel prompting technique, "conditional Variational-autoencoder-Like Prompt" (VLPrompt), which enables the generation of highly convincing fake news articles. VLPrompt…

Prompt layer
Injection
Model layer
Extraction
Data security
Integrity
Safety
BibTeX citation

Paper-evaluated models

No paper-evaluated models are recorded for this entry.

Description

Large Language Models (LLMs) are vulnerable to a novel prompting technique, "conditional Variational-autoencoder-Like Prompt" (VLPrompt), which enables the generation of highly convincing fake news articles. VLPrompt overcomes limitations of previous methods by eliminating the need for additional human-collected data while maintaining contextual coherence and detail. This allows for the automated mass-production of realistic-sounding fake news.

Examples

See the paper's repository for examples of VLPrompt attacks and the resulting fake news articles. Specific examples are shown in Figures 3 and 4 of the paper.

Impact

The vulnerability enables the creation and dissemination of highly believable fake news, potentially causing significant societal harm. This includes the spread of misinformation in sensitive areas like healthcare, manipulation of public opinion, and erosion of trust in legitimate news sources. The high success rate of the VLPrompt technique makes automated detection challenging.

Affected Systems

All LLMs susceptible to the VLPrompt technique and similar prompt engineering approaches. Specific LLMs tested included GPT-4, Vicuna, and others.

Mitigation Steps

  • Improved Prompt Engineering: Develop robust prompt designs that are less susceptible to manipulation and adversarial attacks.
  • Enhanced Detection Models: Develop and train advanced detection models capable of identifying subtle linguistic patterns and inconsistencies in LLM-generated text. Consider training models specifically on examples of VLPrompt and similar attacks.
  • Data Augmentation: Enhance training datasets for fake news detection models to include samples generated using VLPrompt-type attacks.
  • Transparency and Education: Improve public awareness of LLM capabilities for generating realistic-sounding fake news. Educate users how to identify potential misinformation.

Research context and confidence

Evidence and verification
Paper-reported; independent reproduction is not documented.
Primary research source linked.
Severity
Not rated by this catalog.
Source and publication type
arXiv · Research preprint.
Peer-review status is not provided by this source.
Author and publication status
Author metadata is not stored; see the primary paper.
Threat model and attacker access
Ability to influence untrusted model inputs or connected content.
Related deployment categories
No related deployment category is classified.
Taxonomy labels only; paper-specific deployment prerequisites are not inferred.
Affected systems
All LLMs susceptible to the VLPrompt technique and similar prompt engineering approaches. Specific LLMs tested included GPT-4, Vicuna, and others.

Research Paper

Exploring the deceptive power of llm-generated fake news: A study of real-world detection challenges

Primary source: arXiv. Findings are reported by the cited research and have not been independently verified.

View Paper

Evidence

This entry is based on a primary research source. Its findings are paper-reported; independent reproduction and verification are not claimed.

https://arxiv.org/abs/2403.18249

Related research