Related papers: GenAI Confessions: Black-box Membership Inference …
Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or object parts) by linking internal representations to class predictions, thereby bridging…
Generative AI (GenAI) is transforming filmmaking, equipping artists with tools like text-to-image and image-to-video diffusion, neural radiance fields, avatar generation, and 3D synthesis. This paper examines the adoption of these…
Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing data leakage. However, many current state-of-the-art attacks require access to models'…
Text-to-image generative models can produce photo-realistic images for an extremely broad range of concepts, and their usage has proliferated widely among the general public. On the flip side, these models have numerous drawbacks, including…
Adversarial attacks on image classification systems have always been an important problem in the field of machine learning, and generative adversarial networks (GANs), as popular models in the field of image generation, have been widely…
"Does generative AI infringe copyright?" is an urgent question. It is also a difficult question, for two reasons. First, "generative AI" is not just one product from one company. It is a catch-all name for a massive ecosystem of loosely…
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…
As generative Artificial Intelligence (AI) advances, the realism of AI generated imagery has reached a threshold capable of deceiving even vigilant human observers. Yet, while current AI-generated Image Detection (AID) approaches perform…
Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches…
Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked…
New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and…
Much of the state-of-the-art in image synthesis inspired by real artwork are either entirely generative by filtered random noise or inspired by the transfer of style. This work explores the application of image inpainting to continue famous…
Generative artificial intelligence (GenAI) models are increasingly used for scientific data generation, yet their alignment with empirical knowledge in urban science remains unclear. Here, we introduce AI4US (Artificial Intelligence for…
Text-to-image generative models often reflect the biases of the training data, leading to unequal representations of underrepresented groups. This study investigates inclusive text-to-image generative models that generate images based on…
Generative A.I. models have emerged as versatile tools across diverse industries, with applications in privacy-preserving data sharing, computational art, personalization of products and services, and immersive entertainment. Here, we…
Adversarial examples have posed a severe threat to deep neural networks due to their transferable nature. Currently, various works have paid great efforts to enhance the cross-model transferability, which mostly assume the substitute model…
Test Input Generators (TIGs) are crucial to assess the ability of Deep Learning (DL) image classifiers to provide correct predictions for inputs beyond their training and test sets. Recent advancements in Generative AI (GenAI) models have…
Generative models are now capable of producing highly realistic images that look nearly indistinguishable from the data on which they are trained. This raises the question: if we have good enough generative models, do we still need…
Generative artificial intelligence (GenAI) text-to-image systems are increasingly used to generate architectural imagery, yet their capacity to reproduce accurate images in a historically rule-bound field remains poorly characterized. We…
An open secret in contemporary machine learning is that many models work beautifully on standard benchmarks but fail to generalize outside the lab. This has been attributed to biased training data, which provide poor coverage over real…