The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand, more and more attention is paid to unrestricted model accesses that may bring malicious privacy risks of data leakage. To address these issues, many recent works propose privacy-preserving language models (PPLMs) with differential privacy (DP). Unfortunately, different DP implementations make it challenging for a fair comparison among existing PPLMs. In this paper, we present PrivLM-Bench, a multi-perspective privacy evaluation benchmark to empirically and intuitively quantify the privacy leakage of LMs. Instead of only reporting DP parameters, PrivLM-Bench sheds light on the neglected inference data privacy during actual usage. PrivLM-Bench first clearly defines multi-faceted privacy objectives. Then, PrivLM-Bench constructs a unified pipeline to perform private fine-tuning. Lastly, PrivLM-Bench performs existing privacy attacks on LMs with pre-defined privacy objectives as the empirical evaluation results. The empirical attack results are used to fairly and intuitively evaluate the privacy leakage of various PPLMs. We conduct extensive experiments on three datasets of GLUE for mainstream LMs.
Benchmarking Differential Privacy and Federated Learning for BERT Models
Manipal Institute of Technology(马尼帕尔理工学院);Carnegie Mellon University(卡内基梅隆大学);OpenMined;Yildiz Technical University(耶尔德兹技术大学);Ford Motor Company(福特汽车公司);University of California, San Diego(加州大学圣地亚哥分校)
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
The University of Sydney(悉尼大学);University of Queensland(昆士兰大学);Southeast University(东南大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Beihang University(北航);Harbin Institute of Technology(哈尔滨工业大学);Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));The University of Hong Kong(香港大学)
ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));Microsoft(微软);ELLIS Institute Tübingen and MPI for Intelligent Systems(图宾根ELLIS研究所和智能系统研究所);Tübingen AI Center(图宾根人工智能中心)
PII-Bench: Evaluating Query-Aware Privacy Protection Systems
Institute of Fintech, Fudan University(复旦大学金融科技学院);Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University(复旦大学数据科学上海重点实验室);Laboratory of Data Analytics and Security, Fudan University(复旦大学数据安全分析实验室)
Socially-Intelligent Artificial Systems Group, University of Amsterdam(智能社会人工智能系统组,阿姆斯特丹大学);University of Amsterdam(阿姆斯特丹大学);Fundamental AI Lab, University of Technology Nuremberg(基础人工智能实验室,纽伦堡技术大学)
Loose Lips: Understanding Privacy Leakage in Agentic Dialogue
Mila – Quebec AI Institute(米拉-魁北克人工智能研究所);McGill University(麦吉尔大学);Simon Fraser University(西蒙菲莎大学);ÉTS(ÉTS(魁北克大学工程与技术学院));ServiceNow AI Research(ServiceNow人工智能研究部);Université de Montréal(蒙特利尔大学)