中文
相关论文

相关论文: Improving Interpretability and Robustness for the …

200 篇论文

Rapid advances in generative AI have enabled the creation of highly realistic synthetic images, which, while beneficial in many domains, also pose serious risks in terms of disinformation, fraud, and other malicious applications. Current…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Aref Azizpour , Tai D. Nguyen , Matthew C. Stamm

The rapid advancement of generative AI has enabled the creation of highly photorealistic visual content, offering practical substitutes for real images and videos in scenarios where acquiring real data is difficult or expensive. However,…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Aniruddha Mukherjee , Spriha Dubey , Somdyuti Paul

The image deepfake detection task has been greatly addressed by the scientific community to discriminate real images from those generated by Artificial Intelligence (AI) models: a binary classification task. In this work, the deepfake…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Luca Guarnera , Oliver Giudice , Sebastiano Battiato

This paper introduces AIDetx, a novel method for detecting machine-generated text using data compression techniques. Traditional approaches, such as deep learning classifiers, often suffer from high computational costs and limited…

计算与语言 · 计算机科学 2024-12-02 Leonardo Almeida , Pedro Rodrigues , Diogo Magalhães , Armando J. Pinho , Diogo Pratas

Recent advancements in image synthesis, particularly with the advent of GAN and Diffusion models, have amplified public concerns regarding the dissemination of disinformation. To address such concerns, numerous AI-generated Image (AIGI)…

计算机视觉与模式识别 · 计算机科学 2026-02-16 Yunfeng Diao , Naixin Zhai , Changtao Miao , Zitong Yu , Xingxing Wei , Xun Yang , Meng Wang

Watermarking embeds information into digital content like images, audio, or text, imperceptible to humans but robustly detectable by specific algorithms. This technology has important applications in many challenges of the industry such as…

密码学与安全 · 计算机科学 2025-02-11 Pierre Fernandez

AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, and resolution downsampling. We observe that state-of-the-art methods, including B-Free,…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Zongyou Yang , Yinghan Hou , Xiaokun Yang

Recent generative models produce images with a level of authenticity that makes them nearly indistinguishable from real photos and artwork. Potential harmful use cases of these models, necessitate the creation of robust synthetic image…

计算机视觉与模式识别 · 计算机科学 2025-01-15 Delyan Boychev , Radostin Cholakov

AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and visual modalities. A strongly generalizable detector should remain robust under…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Zhengcen Li , Chenyang Jiang , Liangxu Su , Tong Shao , Shiyang Zhou , Ming Tao , Jingyong Su

The advent of deep learning has brought a significant improvement in the quality of generated media. However, with the increased level of photorealism, synthetic media are becoming hardly distinguishable from real ones, raising serious…

计算机视觉与模式识别 · 计算机科学 2021-04-07 Diego Gragnaniello , Davide Cozzolino , Francesco Marra , Giovanni Poggi , Luisa Verdoliva

Advancements in text-to-image generative AI with large multimodal models are spreading into the field of image compression, creating high-quality representation of images at extremely low bit rates. This work introduces novel components to…

图像与视频处理 · 电气工程与系统科学 2025-06-02 Cheng-Lin Wu , Hyomin Choi , Ivan V. Bajić

This paper proposes a method for OOD detection. Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network. We…

计算机视觉与模式识别 · 计算机科学 2021-01-08 Engkarat Techapanurak , Anh-Chuong Dang , Takayuki Okatani

Understanding why a classification model prefers one class over another for an input instance is the challenge of contrastive explanation. This work implements concept-based contrastive explanations for image classification by leveraging…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Yuliia Kaidashova , Bettina Finzel , Ute Schmid

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

机器学习 · 计算机科学 2025-06-04 Tianci Liu , Tong Yang , Quan Zhang , Qi Lei

The rise of advanced AI models like Generative Adversarial Networks (GANs) and diffusion models such as Stable Diffusion has made the creation of highly realistic images accessible, posing risks of misuse in misinformation and manipulation.…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Justin Jiang

Context-based detection methods such as DetectGPT achieve strong generalization in identifying AI-generated text by evaluating content compatibility with a model's learned distribution. In contrast, existing image detectors rely on…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Minsuk Jang , Hyunseo Jeong , Minseok Son , Changick Kim

The rapid growth of the Internet, driven by social media, web browsing, and video streaming, has made images central to the Web experience, resulting in significant data transfer and increased webpage sizes. Traditional image compression…

网络与互联网体系结构 · 计算机科学 2024-07-08 Shayan Ali Hassan , Danish Humair , Ihsan Ayyub Qazi , Zafar Ayyub Qazi

Modern image editors can produce identity-preserving AIGC (IP-AIGC), where the same person appears with new attire, background, or lighting. The robustness and fairness of current detectors in this regime remain unclear, especially for…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Vishal Dubey , Pallavi Tyagi

The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image forgery detection systems. Existing methods, whether non-LLM-based or LLM-based, exhibit…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Qing Huang , Zhipei Xu , Xuanyu Zhang , Xiangyu Yu , Jian Zhang

The generative model has made significant advancements in the creation of realistic videos, which causes security issues. However, this emerging risk has not been adequately addressed due to the absence of a benchmark dataset for…

计算机视觉与模式识别 · 计算机科学 2024-05-08 Peisong He , Leyao Zhu , Jiaxing Li , Shiqi Wang , Haoliang Li