Related papers: Killing One Bird with Two Stones: Model Extraction…

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is…

In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model…

The field of Natural Language Processing (NLP) is currently undergoing a revolutionary transformation driven by the power of pre-trained Large Language Models (LLMs) based on groundbreaking Transformer architectures. As the frequency and…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

E-commerce platforms require structured product data in the form of attribute-value pairs to offer features such as faceted product search or attribute-based product comparison. However, vendors often provide unstructured product…

Motivated by the promising performance of pre-trained language models, we investigate BERT in an evidence retrieval and claim verification pipeline for the FEVER fact extraction and verification challenge. To this end, we propose to use two…

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…

Attribute inference - the process of analyzing publicly available data in order to uncover hidden information - has become a major threat to privacy, given the recent technological leap in machine learning. One way to tackle this threat is…

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to show a model is sufficiently protected against broader memorization risks. However, we…

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present…

Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in…

Over the past few decades, Artificial Intelligence(AI) has progressed from the initial machine learning stage to the deep learning stage, and now to the stage of foundational models. Foundational models have the characteristics of…

The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…

Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies, however, show that such BERT-based models are vulnerable facing the threats of textual adversarial…

In this paper, we report our method for the Information Extraction task in 2019 Language and Intelligence Challenge. We incorporate BERT into the multi-head selection framework for joint entity-relation extraction. This model extends…