Syntax-Oriented Shortcut: A Syntax Level Perturbing Algorithm for Preventing Text Data From Being Learned
inforesearchPeer-ReviewedLLM-Specific
researchsecurity
Source: IEEE Xplore (Security & AI Journals)October 6, 2025
Summary
Researchers created a method called UTE-SS (Unlearnable text examples generation via syntax-oriented shortcut) to protect text data from being used to train AI models without permission. The method adds small, hard-to-notice changes to text by altering its syntax (grammatical structure) so that language models learn misleading patterns instead of useful information, making the text data effectively useless for training.
Classification
Attack Type
Data Extraction
Attack SophisticationModerate
Impact (CIA+S)
confidentiality
AI Component TargetedTraining Data
Related Issues
Monthly digest — independent AI security research
Original source: http://ieeexplore.ieee.org/document/11192553
First tracked: February 12, 2026 at 02:22 PM
Classified by LLM (prompt v3) · confidence: 85%