Related papers: TMI! Finetuned Models Leak Private Information fro…
Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients'…
Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to…
Fine-tuning large language models (LLMs) with local data is a widely adopted approach for organizations seeking to adapt LLMs to their specific domains. Given the shared characteristics in data across different organizations, the idea of…
Machine learning models leak information about their training data every time they reveal a prediction. This is problematic when the training data needs to remain private. Private prediction methods limit how much information about the…
Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perform this task, unfortunately they can leak training data…
As the landscape of large language models expands, efficiently finetuning for specific tasks becomes increasingly crucial. At the same time, the landscape of parameter-efficient finetuning methods rapidly expands. Consequently,…
The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning systems. As these systems are increasingly deployed in critical areas, ensuring their…
Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…
Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to…
Diffusion models have recently gained significant attention in both academia and industry due to their impressive generative performance in terms of both sampling quality and distribution coverage. Accordingly, proposals are made for…
Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially…
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique…
With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the…
Proactive approaches to security, such as adversary emulation, leverage information about threat actors and their techniques (Cyber Threat Intelligence, CTI). However, most CTI still comes in unstructured forms (i.e., natural language),…
Public pretraining is a promising approach to improve differentially private model training. However, recent work has noted that many positive research results studying this paradigm only consider in-distribution tasks, and may not apply to…
Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One of the linchpins for efficiency and accuracy in machine…
In the evolving landscape of machine learning (ML), Federated Learning (FL) presents a paradigm shift towards decentralized model training while preserving user data privacy. This paper introduces the concept of ``privacy drift", an…
While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by…