67 citations · 182 across the 41 of their papers we have counts for
8 papers · 1 filter
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
Bilgehan Sel, Xuanli He, Alwin Peng +2
Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an a…
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…
Attacks on Third-Party APIs of Large Language Models
Wanru Zhao, Vidit Khazanchi, Haodi Xing +3
Large language model (LLM) services have recently begun offering a plugin ecosystem to interact with third-party API services. This innovation enhances the capabilities of LLMs, bu…
Extracted BERT Model Leaks More Information than You Think!
Xuanli He, Chen Chen, Lingjuan Lyu +1
The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing…
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks
Xuanli He, Qiongkai Xu, Yi Zeng +4
Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, a recent…
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
Xuanli He, Qiongkai Xu, Lingjuan Lyu +2
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have been encapsulat…
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
Qiongkai Xu, Xuanli He, Lingjuan Lyu +2
Machine-learning-as-a-service (MLaaS) has attracted millions of users to their splendid large-scale models. Although published as black-box APIs, the valuable models behind these s…
Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs
Chen Chen, Xuanli He, Lingjuan Lyu +1
The collection and availability of big data, combined with advances in pre-trained models (e.g., BERT, XLNET, etc), have revolutionized the predictive performance of modern natural…