Spinning Sequence-to-Sequence Models with Meta-Backdoors

22 July 2021

Papers citing "Spinning Sequence-to-Sequence Models with Meta-Backdoors"

8 / 8 papers shown

Title
Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs Himanshu Beniwal Sailesh Panda Mayank Singh 35 0 0 24 Feb 2025
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models Max Lamparth Anka Reuel KELM 28 10 0 24 Feb 2023
Co-Writing with Opinionated Language Models Affects Users' Views Maurice Jakesch Advait Bhat Daniel Buschek Lior Zalmanson Mor Naaman ELM 41 204 0 01 Feb 2023
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training Zhenting Wang Hailun Ding Juan Zhai Shiqing Ma AAML 6 45 0 13 Feb 2022
A General Framework for Defending Against Backdoor Attacks via Influence Graph Xiaofei Sun Jiwei Li Xiaoya Li Ziyao Wang Tianwei Zhang Han Qiu Fei Wu Chun Fan AAML TDI 17 5 0 29 Nov 2021
Concealed Data Poisoning Attacks on NLP Models Eric Wallace Tony Zhao Shi Feng Sameer Singh SILM 6 18 0 23 Oct 2020
It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations Samson Tan Shafiq R. Joty Min-Yen Kan R. Socher 158 103 0 09 May 2020
Generating Natural Language Adversarial Examples M. Alzantot Yash Sharma Ahmed Elgohary Bo-Jhang Ho Mani B. Srivastava Kai-Wei Chang AAML 243 914 0 21 Apr 2018