Related papers: A Mutation-based Text Generation for Adversarial M…
In the context of generative models, text-to-image generation achieved impressive results in recent years. Models using different approaches were proposed and trained in huge datasets of pairs of texts and images. However, some methods rely…
The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information. Thus, it is critical for the generated response to be natural and fluent. We propose to…
Recent advancements in natural language generation has raised serious concerns. High-performance language models are widely used for language generation tasks because they are able to produce fluent and meaningful sentences. These models…
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…
Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are…
Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial…
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 Language Models (LLMs) possess an extraordinary capability to produce text that is not only coherent and contextually relevant but also strikingly similar to human writing. They adapt to various styles and genres, producing content…
Generative Adversarial Networks (GAN) is a model for data synthesis, which creates plausible data through the competition of generator and discriminator. Although GAN application to image synthesis is extensively studied, it has inherent…
Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…
Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.…
Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…
Synthetic text generation is challenging and has limited success. Recently, a new architecture, called Transformers, allow machine learning models to understand better sequential data, such as translation or summarization. BERT and GPT-2,…
The increasing capability of large language models (LLMs) to generate fluent long-form texts is presenting new challenges in distinguishing machine-generated outputs from human-written ones, which is crucial for ensuring authenticity and…
When generating text from probabilistic models, the chosen decoding strategy has a profound effect on the resulting text. Yet the properties elicited by various decoding strategies do not always transfer across natural language generation…
Deep neural networks for natural language processing tasks are vulnerable to adversarial input perturbations. In this paper, we present a versatile language for programmatically specifying string transformations -- e.g., insertions,…
Machine-Generated Text (MGT) detection aims to identify a piece of text as machine or human written. Prior work has primarily formulated MGT detection as a binary classification task over an entire document, with limited work exploring…
Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…
The ability of large language models to generate complex texts allows them to be widely integrated into many aspects of life, and their output can quickly fill all network resources. As the impact of LLMs grows, it becomes increasingly…
Many problems in database systems, such as cardinality estimation, database testing and optimizer tuning, require a large query load as data. However, it is often difficult to obtain a large number of real queries from users due to user…