Related papers: ToxiGAN: Toxic Data Augmentation via LLM-Guided Di…

Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In this work, we exploit this property to generate adversarial…

The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared with state-of-the-art models. In this paper, we propose a…

Generative adversarial networks (GANs) have made remarkable achievements in synthesizing images in recent years. Typically, training GANs requires massive data, and the performance of GANs deteriorates significantly when training data is…

In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution…

Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but often computationally intensive. Recent strides in diffusion…

Online social media is rife with offensive and hateful comments, prompting the need for their automatic detection given the sheer amount of posts created every second. Creating high-quality human-labelled datasets for this task is difficult…

Natural language generation (NLG) is one of the most impactful fields in NLP, and recent years have witnessed its evolution brought about by large language models (LLMs). As the key instrument for writing assistance applications, they are…

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifically, we explore whether high accuracy classifiers can be built from small datasets, utilizing a combination of data augmentation techniques and…

Conditional image generation is an active research topic including text2image and image translation. Recently image manipulation with linguistic instruction brings new challenges of multimodal conditional generation. However, traditional…

In this paper, we present a simple approach to train Generative Adversarial Networks (GANs) in order to avoid a \textit {mode collapse} issue. Implicit models such as GANs tend to generate better samples compared to explicit models that are…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Relation extraction models suffer from limited qualified training data. Using human annotators to label sentences is too expensive and does not scale well especially when dealing with large datasets. In this paper, we use Auxiliary…

Recent advancements in large language models (LLMs) have remarkably enhanced performances on a variety of tasks in multiple languages. However, tokenizers in LLMs trained primarily on English-centric corpora often overly fragment a text…

In this paper, in order to further deal with the performance degradation caused by ignoring the phase information in conventional speech enhancement systems, we proposed a temporal dilated convolutional generative adversarial network…

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs.…

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

Robust content moderation classifiers are essential for the safety of Generative AI systems. In this task, differences between safe and unsafe inputs are often extremely subtle, making it difficult for classifiers (and indeed, even humans)…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…