2 citations · 5 across the 22 of their papers we have counts for
6 papers · 1 filter
Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy
Weijun Li, Arnaud Grivet Sébert, Qiongkai Xu +2
The growing use of large language models has increased interest in sharing textual data in a privacy-preserving manner. One prominent line of work addresses this challenge through…
Defending against Backdoor Attacks via Module Switching
Weijun Li, Ansh Arora, Xuanli He +2
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabil…
ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation
Yiyi Chen, Qiongkai Xu, Johannes Bjerva
With the growing popularity of Large Language Models (LLMs) and vector databases, private textual data is increasingly processed and stored as numerical embeddings. However, recent…
WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
Anudeex Shetty, Qiongkai Xu, Jey Han Lau
Embeddings-as-a-Service (EaaS) is a service offered by large language model (LLM) developers to supply embeddings generated by LLMs. Previous research suggests that EaaS is prone t…
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
Anudeex Shetty, Yue Teng, Ke He +1
Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature extraction capabilities for addressing various downstream tasks in Natural Language Process…
Fingerprint Attack: Client De-Anonymization in Federated Learning
Qiongkai Xu, Trevor Cohn, Olga Ohrimenko
Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another. Privacy can be further improve…