A unified detection and unlearning framework identifies and mitigates data poisoning in summarization models, achieving 85-92% detection and up to 96% behavior restoration across multiple architectures.
Semattack: natural textual attacks via differ- ent semantic spaces.arXiv preprint arXiv:2205.01287, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
A unified detection and unlearning framework identifies and mitigates data poisoning in summarization models, achieving 85-92% detection and up to 96% behavior restoration across multiple architectures.