Related papers: Where Detectors Fail: Probing Generative Space for…

The rapid progression of generative AI (GenAI) technologies has heightened concerns regarding the misuse of AI-generated imagery. To address this issue, robust detection methods have emerged as particularly compelling, especially in…

High-fidelity generative models have narrowed the perceptual gap between synthetic and real images, posing serious threats to media security. Most existing AI-generated image (AIGI) detectors rely on artifact-based classification and…

Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied.…

The rapid progress of visual generative models has made AI-generated images increasingly difficult to distinguish from authentic ones, posing growing risks to social trust and information integrity. This motivates detectors that are not…

Recent advances in generative AI have brought incredible breakthroughs in several areas, including medical imaging. These generative models have tremendous potential not only to help safely share medical data via synthetic datasets but also…

With the rapid evolution of AI Generated Content (AIGC), forged images produced through this technology are inherently more deceptive and require less human intervention compared to traditional Computer-generated Graphics (CG). However,…

Generative models can now produce photorealistic synthetic data which is virtually indistinguishable from the real data used to train it. This is a significant evolution over previous models which could produce reasonable facsimiles of the…

The rapid evolution of AI-generated images poses growing challenges to information integrity and media authenticity. Existing detection approaches face limitations in robustness, interpretability, and generalization across diverse…

As state-of-the-art language models continue to improve, the need for robust detection of machine-generated text becomes increasingly critical. However, current state-of-the-art machine text detectors struggle to adapt to new unseen domains…

Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…

As large language model-based chat systems become increasingly widely used, generative engine optimization (GEO) has emerged as an important problem for information access and retrieval. In classical search engines, results are…

Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial, yet current detectors often struggle to generalize in…

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…

Plagiarism in programming courses remains a persistent challenge, especially in competitive programming contexts where assignments often have unique, known solutions. This paper examines why traditional code plagiarism detection methods…

Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps.…

As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models…

This paper introduces a novel generative encoder (GE) model for generative imaging and image processing with applications in compressed sensing and imaging, image compression, denoising, inpainting, deblurring, and super-resolution. The GE…

As generative technologies advance, visual content has evolved into a complex mix of natural and AI-generated images, driving the need for more efficient coding techniques that prioritize perceptual quality. Traditional codecs and learned…

The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be collected by commercial organizations without consent and used…

As generative models become increasingly diverse and powerful, cross-generator detection has emerged as a new challenge. Existing detection methods often memorize artifacts of specific generative models rather than learning transferable…