Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs

Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs

29 August 2021

Gholamreza Haffari

Papers citing "Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs"

15 / 15 papers shown

Title
WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks Anudeex Shetty Qiongkai Xu Jey Han Lau WaLM 26 2 0 29 Aug 2024
ModelShield: Adaptive and Robust Watermark against Model Extraction Attack Kaiyi Pang Tao Qi Chuhan Wu Minhao Bai Minghu Jiang Yongfeng Huang AAML WaLM 59 2 0 03 May 2024
Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation Di Mi Yanjun Zhang Leo Yu Zhang Shengshan Hu Qi Zhong Haizhuan Yuan Shirui Pan AAML 28 2 0 12 Mar 2024
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection Anudeex Shetty Yue Teng Ke He Qiongkai Xu WaLM 17 5 0 03 Mar 2024
Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation Aditya Desu Xuanli He Qiongkai Xu Wei Lu WIGM 14 1 0 23 Feb 2024
Stolen Subwords: Importance of Vocabularies for Machine Translation Model Stealing Vilém Zouhar AAML 17 0 0 29 Jan 2024
MeaeQ: Mount Model Extraction Attacks with Efficient Queries Chengwei Dai Minxuan Lv Kun Li Wei Zhou AAML 11 2 0 21 Oct 2023
When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions Weiming Zhuang Chen Chen Lingjuan Lyu C. L. P. Chen Yaochu Jin Lingjuan Lyu AIFin AI4CE 83 84 0 27 Jun 2023
Protecting Language Generation Models via Invisible Watermarking Xuandong Zhao Yu-Xiang Wang Lei Li WaLM 9 80 0 06 Feb 2023
Extracted BERT Model Leaks More Information than You Think! Xuanli He Chen Chen Lingjuan Lyu Qiongkai Xu SILM MIACV 15 5 0 21 Oct 2022
IDEAL: Query-Efficient Data-Free Learning from Black-box Models Jie M. Zhang Chen Chen Lingjuan Lyu 52 14 0 23 May 2022
Semantics-Preserved Distortion for Personal Privacy Protection in Information Management Jiajia Li P. Wang Letian Peng Shitou Zhang Xueyi Li Zuchao Li Haihui Zhao 8 1 0 04 Jan 2022
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark Xuanli He Qiongkai Xu Lingjuan Lyu Fangzhao Wu Chenguang Wang WaLM 160 92 0 05 Dec 2021
Data Augmentation using Pre-trained Transformer Models Varun Kumar Ashutosh Choudhary Eunah Cho VLM 209 315 0 04 Mar 2020
Large scale distributed neural network training through online distillation Rohan Anil Gabriel Pereyra Alexandre Passos Róbert Ormándi George E. Dahl Geoffrey E. Hinton FedML 267 402 0 09 Apr 2018