Conference
Open access
Aug 2026
Evaluating the Robustness of Transformer-based Models Against Data Poisoning Attacks in Social Media Sentiment Analysis
A baseline resilience study of BERT, RoBERTa, and BERTweet against three increasingly complex adversarial attacks: label flipping, trigger injection, and clean-label poisoning shows the domain-aligned BERTweet model demonstrated the highest baseline resilience to these specific manipulations.
Clarencia Augustine, Devon Nicholas, Vania Alicia Yocelin et al.
· International Conferences on... · 0 citations