相关论文: Spoofing Attacker Also Benefits from Self-Supervis…

Current trends in audio anti-spoofing detection research strive to improve models' ability to generalize across unseen attacks by learning to identify a variety of spoofing artifacts. This emphasis has primarily focused on the spoof class.…

Information on speaker characteristics can be useful as side information in improving speaker recognition accuracy. However, such information is often private. This paper investigates how privacy-preserving learning can improve a speaker…

Large neural language models trained on massive amounts of text have emerged as a formidable strategy for Natural Language Understanding tasks. However, the strength of these models as Natural Language Generators is less clear. Though…

Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These representations encode similarity structures that enable…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Recent advancements in adversarial attacks have demonstrated their effectiveness in misleading speaker recognition models, making wrong predictions about speaker identities. On the other hand, defense techniques against speaker-adversarial…

Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…

The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice…

Generative models learn the distribution of data from a sample dataset and can then generate new data instances. Recent advances in deep learning has brought forth improvements in generative model architectures, and some state-of-the-art…

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Pre-trained language models have brought significant improvements in performance in a variety of natural language processing tasks. Most existing models performing state-of-the-art results have shown their approaches in the separate…

We analyze the masked language modeling pretraining objective function from the perspective of the distributional hypothesis. We investigate whether better sample efficiency and the better generalization capability of models pretrained with…

Large language models are trained on massive scrapes of the web, as required by current scaling laws. Most progress is made for English, given its abundance of high-quality pretraining data. For most other languages, however, such high…

Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a…

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adversaries can `steal' deployed models even when they have no…