Related papers: Robust AI-Generated Text Detection by Restricted E…
The growing use of large language models (LLMs) for text generation has led to widespread concerns about AI-generated content detection. However, an overlooked challenge is AI-polished text, where human-written content undergoes subtle…
Scene text detection based on deep neural networks have progressed substantially over the past years. However, previous state-of-the-art methods may still fall short when dealing with challenging public benchmarks because the performances…
Generative adversarial networks (GANs) and diffusion models have recently achieved state-of-the-art performance in audio super-resolution (ADSR), producing perceptually convincing wideband audio from narrowband inputs. However, existing…
The recent rise in capabilities of AI-based music generation tools has created an upheaval in the music industry, necessitating the creation of accurate methods to detect such AI-generated content. This can be done using audio-based…
The burgeoning progress in the field of Large Language Models (LLMs) heralds significant benefits due to their unparalleled capacities. However, it is critical to acknowledge the potential misuse of these models, which could give rise to a…
AI-text detectors achieve high accuracy on in-domain benchmarks, but often struggle to generalize across different generation conditions such as unseen prompts, model families, or domains. While prior work has reported these generalization…
In this paper, we study the surprising impact that truncating text embeddings has on downstream performance. We consistently observe across 6 state-of-the-art text encoders and 26 downstream tasks, that randomly removing up to 50% of…
The rapid development of Artificial Intelligence (AI) has led to the creation of powerful text generation models, such as large language models (LLMs), which are widely used for diverse applications. However, concerns surrounding…
Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints. In this respect, we hypothesize that while large language models excel…
Training a good deep learning model requires substantial data and computing resources, which makes the resulting neural model a valuable intellectual property. To prevent the neural network from being undesirably exploited, non-transferable…
Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning models neglect the importance of modeling context information,…
Motivated by the increasing popularity of transformers in computer vision, in recent times there has been a rapid development of novel architectures. While in-domain performance follows a constant, upward trend, properties like robustness…
With the advent of fluent generative language models that can produce convincing utterances very similar to those written by humans, distinguishing whether a piece of text is machine-generated or human-written becomes more challenging and…
The large language models (LLMs) are able to generate high-quality texts in multiple languages. Such texts are often not recognizable by humans as generated, and therefore present a potential of LLMs for misuse (e.g., plagiarism, spams,…
$ $The usage of generative artificial intelligence (AI) tools based on large language models, including ChatGPT, Bard, and Claude, for text generation has many exciting applications with the potential for phenomenal productivity gains. One…
Network embedding aims to learn a latent, low-dimensional vector representations of network nodes, effective in supporting various network analytic tasks. While prior arts on network embedding focus primarily on preserving network topology…
Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…
Deepfakes, created using advanced AI techniques such as Variational Autoencoder and Generative Adversarial Networks, have evolved from research and entertainment applications into tools for malicious activities, posing significant threats…
Recent text detection frameworks require several handcrafted components such as anchor generation, non-maximum suppression (NMS), or multiple processing stages (e.g. label generation) to detect arbitrarily shaped text images. In contrast,…
In this work, we compile $\textbf{$\texttt{DroidCollection}$}$, the most extensive open data suite for training and evaluating machine-generated code detectors, comprising over a million code samples, seven programming languages, outputs…