相关论文: Text Revealer: Private Text Reconstruction via Mod…

In recent years, the fields of natural language processing (NLP) and information retrieval (IR) have made tremendous progress thanksto deep learning models like Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs) and Long…

We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5, enables simple, end-to-end transformer based models to outperform pipelined neural architectures…

Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative…

Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement…

Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can reconstruct data samples from language models, making this…

We present a study on the efficacy of adversarial training on transformer neural network models, with respect to the task of detecting check-worthy claims. In this work, we introduce the first adversarially-regularized, transformer-based…

Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses…

With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…

We present ReadOnce Transformers, an approach to convert a transformer-based model into one that can build an information-capturing, task-independent, and compressed representation of text. The resulting representation is reusable across…

State-of-the-art text classification models are becoming increasingly reliant on deep neural networks (DNNs). Due to their black-box nature, faithful and robust explanation methods need to accompany classifiers for deployment in real-life…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial…

We propose the first general-purpose gradient-based attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix,…

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract…

Personalized Large Language Models (LLMs) have become increasingly prevalent, showcasing the impressive capabilities of models like GPT-4. This trend has also catalyzed extensive research on deploying LLMs on mobile devices. Feasible…

Model inversion (MI) attacks allow to reconstruct average per-class representations of a machine learning (ML) model's training data. It has been shown that in scenarios where each class corresponds to a different individual, such as face…

Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also…

Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…

This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a…

Although federated learning has increasingly gained attention in terms of effectively utilizing local devices for data privacy enhancement, recent studies show that publicly shared gradients in the training process can reveal the private…