SecurityJul 16, 2026, 5:56 PM

Pretraining Data Can Be Poisoned through Computational Propaganda

30-second summary

Researchers demonstrate that computational propaganda can poison large language model pretraining data, embedding harmful behaviors that are difficult to detect.

TickrWire
Key takeaways
  • Computational propaganda can effectively poison web-scale pretraining corpora.
  • Attacks via public discussion interfaces bypass limitations of previous Wikipedia-based studies.
  • Poisoned data introduces harmful behaviors that are hard to detect and mitigate.
Full story

Previous studies on data poisoning largely focused on static sources like Wikipedia, which do not reflect the complexity of real-world pretraining corpora. This new paper expands the scope by examining attacks via public discussion interfaces, a mechanism used for computational propaganda at scale.

The authors show that adversaries can inject malicious content into these web-scale pipelines. The study specifically analyzes how this poisoned data interacts with modern data curation and filtering processes used during model training.

Results indicate that these attacks are feasible and effective. They introduce harmful behaviors into the resulting models that persist even after standard safety training and are notably hard to mitigate.

Sponsored
Why this matters
Developers

Highlights the need for robust data sanitization pipelines and source verification.

Businesses

Underscores a critical risk of model alignment failure due to corrupted training inputs.

Investors

Identifies a significant technical vulnerability in the foundation of current AI systems.

Everyone

Shows how online misinformation campaigns can directly influence AI behavior.

Glossary
Computational Propaganda
The use of algorithms, automation, and human curation to manipulate public opinion online.
Data Poisoning
A type of attack where malicious data is inserted into a training set to corrupt the model.
Sources · 1
Read next
More stories
TickrWire
AI Research

QFireNet: A Quantum-Enhanced U-Net for Wildfire Segmentation from Sentinel-2 Imagery

Researchers introduce QFireNet, a quantum-enhanced U-Net model for wildfire segmentation from Sentinel-2 imagery, published on arXiv.

TickrWire
AI Tools

Organize your curiosity: Generative AI tools prove adept at structuring volumes of information - Editor and Publisher

Generative AI tools are effective in structuring large volumes of information, helping to organize and make sense of complex data. This development has significant implications for various industries and applications.

TickrWire
AI Research

Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees

Researchers introduce C3R, a method to prevent incorrect domain evidence from polluting multi-domain retrieval tasks. It uses conformal risk control to ensure reliability without needing labels at query time.

TickrWire
AI Research

TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories

Researchers introduced TEDDY, a 1.84‑million‑parameter transformer trained on 73 million ICD‑10 codes from 1.6 million children, to forecast future diagnoses and visit timing.

Sponsored
TickrWire
AI Research

Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video Models

Researchers propose SIRUS, a framework for suppressing target concepts in text-to-video models. This allows for more controlled video generation without retraining the model.

TickrWire
AI Research

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Researchers introduced KeyFrame-Compass, the first comprehensive benchmark designed to evaluate how faithfully video generation models can reproduce specific keyframes while maintaining overall video quality.

TickrWireAI News Intelligence

We aggregate, verify, summarise and explain the latest artificial intelligence news from open, legal sources.

Daily AI digest

Top AI stories, summarised, in your inbox each morning.

© 2026 TickrWire. Summaries and analysis are AI-generated and may contain errors.