TIDE: Making Task-Agnostic Backdoors Harder to Erase in Pre-trained Language Models - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Yan Meng, Zhigang Lu 0001, Bing Li 0002, AnAn Du, Shuchao Pang. TIDE: Making Task-Agnostic Backdoors Harder to Erase in Pre-trained Language Models. In Siqi Ma 0001, Surya Nepal, editors, Information Security and Privacy - 31st Australasian Conference, ACISP 2026, Perth, WA, Australia, July 6-9, 2026, Proceedings, Part II. Volume 16793 of Lecture Notes in Computer Science, pages 265-284, Springer, 2026. [doi]

This author has not been identified. Look up 'Yan Meng' in GoogleThis author has not been identified. Look up 'Zhigang Lu 0001' in GoogleThis author has not been identified. Look up 'Bing Li 0002' in GoogleThis author has not been identified. Look up 'AnAn Du' in GoogleThis author has not been identified. Look up 'Shuchao Pang' in Google

runs on WebDSL