Related papers: Strong Copyright Protection for Language Models vi…

Image-language learning has made unprecedented progress in visual understanding. These developments have come at high costs, as contemporary vision-language models require large model scales and amounts of data. We here propose a much…

Fine-tuning pre-trained models for downstream tasks is a widely adopted technique known for its adaptability and reliability across various domains. Despite its conceptual simplicity, fine-tuning entails several troublesome engineering…

(Natural Language Processing) NLP techniques such as text classification and topic discovery are very useful in many application areas including information retrieval, knowledge discovery, policy formulation, and decision-making. However,…

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the…

Diffusion models have achieved remarkable success in novel view synthesis, but their reliance on large, diverse, and often untraceable Web datasets has raised pressing concerns about image copyright protection. Current methods fall short in…

Programming languages can benefit from one another by utilizing a pre-trained model for software engineering tasks such as code summarization and method name prediction. While full fine-tuning of Code Language Models (Code-LMs) has been…

The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which…

Generative models have achieved impressive results in text to image tasks, significantly advancing visual content creation. However, this progress comes at a cost, as such models rely heavily on large-scale training data and may…

Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-time mitigation methods typically manipulate classifier-free…

Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks. Fine-tuning separate foundation models for many downstream…

Web-based AI image generation has become an innovative art form that can generate novel artworks with the rapid development of the diffusion model. However, this new technique brings potential copyright infringement risks as it may…

Federated Learning Networks (FLNs) have been envisaged as a promising paradigm to collaboratively train models among mobile devices without exposing their local privacy data. Due to the need for frequent model updates and communications,…

With the proliferation of multi-modal data in large-scale visual recognition systems, enabling models to continuously acquire knowledge from evolving data streams while preserving prior information has become increasingly critical.…

Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a…

In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data. However, the global models are often obtained via a performance tradeoff…

There is a growing concern that generative AI models will generate outputs closely resembling the copyrighted materials for which they are trained. This worry has intensified as the quality and complexity of generative models have immensely…

Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications. These adversarial examples tend to be transferable between models, but targeted…

Federated learning (FL) has emerged as a promising learning paradigm in which only local model parameters (gradients) are shared. Private user data never leaves the local devices thus preserving data privacy. However, recent research has…

Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on…

Recent neural sequence-to-sequence models with a copy mechanism have achieved remarkable progress in various text generation tasks. These models addressed out-of-vocabulary problems and facilitated the generation of rare words. However, the…