相关论文: Multi-Granularity Tibetan Textual Adversarial Atta…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the generation of reasonably good speech quality with a single model and made it possible to synthesize the speech of a speaker with limited training data.…

Multi-speaker TTS has to learn both linguistic embedding and text embedding to generate speech of desired linguistic content in desired voice. However, it is unclear which characteristic of speech results from speaker and which part from…

The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diffusion models has…

Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold…

Tactics, Techniques and Procedures (TTPs) represent sophisticated attack patterns in the cybersecurity domain, described encyclopedically in textual knowledge bases. Identifying TTPs in cybersecurity writing, often called TTP mapping, is an…

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

Tibetan is a low-resource language. In order to alleviate the shortage of parallel corpus between Tibetan and Chinese, this paper uses two monolingual corpora and a small number of seed dictionaries to learn the semi-supervised method with…

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this…

Neural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. While previous works have shown that…

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…

Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. However, recent studies reveal that the robustness of these…

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…

Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes generator. While in…

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models…

Although deep learning has made remarkable progress in processing various types of data such as images, text and speech, they are known to be susceptible to adversarial perturbations: perturbations specifically designed and added to the…

Pre-trained language models of code are now widely used in various software engineering tasks such as code generation, code completion, vulnerability detection, etc. This, in turn, poses security and reliability risks to these models. One…