中文
相关论文

相关论文: Simplicity Prevails: The Emergence of Generalizabl…

200 篇论文

With the evolution of Text-to-Image (T2I) models, the quality defects of AI-Generated Images (AIGIs) pose a significant barrier to their widespread adoption. In terms of both perception and alignment, existing models cannot always guarantee…

In AI-generated image detection, current cutting-edge methods typically adapt pre-trained foundation models through partial-parameter fine-tuning. However, these approaches often struggle to generalize to forgeries from unseen generators,…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Yiheng Li , Zichang Tan , Guoqing Xu , Zhen Lei , Xu Zhou , Yang Yang

Detecting assistance from artificial intelligence is increasingly important as they become ubiquitous across complex tasks such as text generation, medical diagnosis, and autonomous driving. Aid detection is challenging for humans,…

人工智能 · 计算机科学 2025-07-16 Tyler King , Nikolos Gurney , John H. Miller , Volkan Ustun

Recent advances in AI-generated content have fueled the rise of highly realistic synthetic videos, posing severe risks to societal trust and digital integrity. Existing benchmarks for video authenticity detection typically suffer from…

计算机视觉与模式识别 · 计算机科学 2025-08-15 Jieyu Li , Xin Zhang , Joey Tianyi Zhou

Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content. While beneficial for many applications, these models also pose significant societal…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Qijie Xu , Can Wang , Jiawei Chen , Siwei Lyu , Defang Chen

Existing state-of-the-art AI-Generated image detection methods mostly consider extracting low-level information from RGB images to help improve the generalization of AI-Generated image detection, such as noise patterns. However, these…

计算机视觉与模式识别 · 计算机科学 2025-07-18 Ziyin Zhou , Ke Sun , Zhongxi Chen , Xianming Lin , Yunpeng Luo , Ke Yan , Shouhong Ding , Xiaoshuai Sun

The widespread adoption of Large Language Models (LLMs) has made the detection of AI-Generated text a pressing and complex challenge. Although many detection systems report high benchmark accuracy, their reliability in real-world settings…

计算与语言 · 计算机科学 2026-04-23 Shushanta Pudasaini , Luis Miralles-Pechuán , David Lillis , Marisa Llorens Salvador

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…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Ruiqi Liu , Manni Cui , Ziheng Qin , Zhiyuan Yan , Ruoxin Chen , Yi Han , Zhiheng Li , Junkai Chen , ZhiJin Chen , Kaiqing Lin , Jialiang Shen , Lubin Weng , Jing Dong , Yan Wang , Shu Wu

Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…

密码学与安全 · 计算机科学 2026-03-12 Sunpill Kim , Chanwoo Hwang , Minsu Kim , Jae Hong Seo

The rapid advancement of Generative Artificial Intelligence (GenAI) capabilities is accompanied by a concerning rise in its misuse. In particular the generation of credible misinformation in the form of images poses a significant threat to…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Sina Mavali , Jonas Ricker , David Pape , Asja Fischer , Lea Schönherr

As large language models (LLMs) generate text that increasingly resembles human writing, the subtle cues that distinguish AI-generated content from human-written content become increasingly challenging to capture. Reliance on…

计算与语言 · 计算机科学 2026-04-16 Xiao Pu , Zepeng Cheng , Lin Yuan , Yu Wu , Xiuli Bi

A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, entangled forgery representation, conflating content-dependent…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Yuncheng Guo , Junyan Ye , Chenjue Zhang , Hengrui Kang , Haohuan Fu , Conghui He , Weijia Li

Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…

Over the past years, image generation and manipulation have achieved remarkable progress due to the rapid development of generative AI based on deep learning. Recent studies have devoted significant efforts to address the problem of face…

计算机视觉与模式识别 · 计算机科学 2024-02-15 Yuhang Lu , Touradj Ebrahimi

The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Davide Cozzolino , Giovanni Poggi , Riccardo Corvi , Matthias Nießner , Luisa Verdoliva

Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators. We trace this failure in part to latent prior bias:…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Yue Zhou , Xinan He , KaiQing Lin , Bin Fan , Feng Ding , Bin Li

Recent advances in Generative AI (GenAI) have led to significant improvements in the quality of generated visual content. As AI-generated visual content becomes increasingly indistinguishable from real content, the challenge of detecting…

计算机视觉与模式识别 · 计算机科学 2025-07-18 Keerthi Veeramachaneni , Praveen Tirupattur , Amrit Singh Bedi , Mubarak Shah

The recent rise of generative artificial intelligence (GenAI) capable of creating scientific images presents a challenge in the fight against academic fraud. This study evaluates the efficacy of three free web-based AI detectors in…

定量方法 · 定量生物学 2024-07-16 Romain-Daniel Gosselin

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…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Despina Konstantinidou , Dimitrios Karageorgiou , Christos Koutlis , Olga Papadopoulou , Emmanouil Schinas , Symeon Papadopoulos

The emergence of advanced AI-based tools to generate realistic images poses significant challenges for forensic detection and source attribution, especially as new generative techniques appear rapidly. Traditional methods often fail to…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Tai D. Nguyen , Aref Azizpour , Matthew C. Stamm