JAIN, Raunit; SHAH, Raaj; KANADIA, Khilan; JAIN, Jinay; GHAG, Dr. Kranti; NARVEKAR, Dr. Meera. Embedding Instability Score for Detecting Backdoor Attacks in NLP Models. International Journal of Artificial Intelligence and Machine Learning, [S. l.], v. 6, n. 3, p. 242–250, 2026. DOI: 10.51483/IJAIML.6.3.2026.242-250. Disponível em: https://svedbergopen.com/index.php/ijaiml/article/view/1715. Acesso em: 14 sep. 2026.