中文
相关论文

相关论文: AudioMarkBench: Benchmarking Robustness of Audio W…

200 篇论文

As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are a promising approach to address the problem of…

Watermarking is an essential technique for embedding an identifier (i.e., watermark message) within digital images to assert ownership and monitor unauthorized alterations. In face recognition systems, watermarking plays a pivotal role in…

计算机视觉与模式识别 · 计算机科学 2024-09-25 Yuguang Yao , Anil Jain , Sijia Liu

With the rapid integration of advanced reasoning capabilities into spoken dialogue models, the field urgently demands benchmarks that transcend simple interactions to address real-world complexity. However, current evaluations predominantly…

计算与语言 · 计算机科学 2026-02-16 Yangzhuo Li , Shengpeng Ji , Yifu Chen , Tianle Liang , Haorong Ying , Yule Wang , Junbo Li , Jun Fang , Zhou Zhao

Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for…

声音 · 计算机科学 2024-12-30 Junzuo Zhou , Jiangyan Yi , Yong Ren , Jianhua Tao , Tao Wang , Chu Yuan Zhang

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…

密码学与安全 · 计算机科学 2026-05-29 Yuexin Li , Wenjie Qu , Linyu Wu , Yulin Chen , Yufei He , Tri Cao , Bryan Hooi , Jiaheng Zhang

A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. This issue leads to unfair performance comparisons and potentially misleading results.…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Zhiyuan Yan , Yong Zhang , Xinhang Yuan , Siwei Lyu , Baoyuan Wu

The availability and easy access to digital communication increase the risk of copyrighted material piracy. In order to detect illegal use or distribution of data, digital watermarking has been proposed as a suitable tool. It protects the…

计算机视觉与模式识别 · 计算机科学 2019-10-04 Bingyang Wen , Sergul Aydore

Text watermarking schemes have gained considerable attention in recent years, yet still face critical challenges in achieving simultaneous robustness, generalizability, and imperceptibility. This paper introduces a new embedding…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Jiale Meng , Yiming Li , Zheming Lu , Zewei He , Hao Luo , Tianwei Zhang

The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages…

密码学与安全 · 计算机科学 2024-11-21 Rui Xu , Mengya Hu , Deren Lei , Yaxi Li , David Lowe , Alex Gorevski , Mingyu Wang , Emily Ching , Alex Deng

Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a…

声音 · 计算机科学 2022-03-16 Yongbaek Cho , Changhoon Kim , Yezhou Yang , Yi Ren

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

计算与语言 · 计算机科学 2026-05-29 Yukang Lin , Jiahao Shao , Shuoran Jiang , Wentao Zhu , Bingjie Lu , Xiangping Wu , Joanna Siebert , Qingcai Chen

Attack detection and mitigation strategies for cyberphysical systems (CPS) are an active area of research, and researchers have developed a variety of attack-detection tools such as dynamic watermarking. However, such methods often make…

系统与控制 · 电气工程与系统科学 2020-04-01 Matt Olfat , Stephen Sloan , Pedro Hespanhol , Matt Porter , Ram Vasudevan , Anil Aswani

Watermarking has emerged as a promising solution to counter harmful or deceptive AI-generated content by embedding hidden identifiers that trace content origins. However, the robustness of current watermarking techniques is still largely…

密码学与安全 · 计算机科学 2025-07-08 Xiaodong Wu , Tianyi Tang , Xiangman Li , Jianbing Ni , Yong Yu

Modern voice cloning, also known as zero-shot text-to-speech (TTS), can synthesize speech that closely matches a target speaker from only seconds of reference audio, enabling applications such as personalized speech interfaces and dubbing.…

声音 · 计算机科学 2026-05-26 Ruinan Jin , Xinting Liao , Hanlin Yu , Deval Pandya , Xiaoxiao Li

The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security. Current AI-driven detection solutions lack explainability and underperform in real-world settings. In…

机器学习 · 计算机科学 2024-10-11 Georgia Channing , Juil Sock , Ronald Clark , Philip Torr , Christian Schroeder de Witt

Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a secret watermark key. A core security threat are forgery…

密码学与安全 · 计算机科学 2026-05-12 Toluwani Aremu , Noor Hussein , Munachiso Nwadike , Samuele Poppi , Jie Zhang , Karthik Nandakumar , Neil Gong , Nils Lukas

Digital watermarks can be embedded into AI-generated content (AIGC) by initializing the generation process with starting points sampled from a secret distribution. When combined with pseudorandom error-correcting codes, such watermarked…

密码学与安全 · 计算机科学 2025-11-13 De Zhang Lee , Han Fang , Hanyi Wang , Ee-Chien Chang

Neural speech generation (NSG) has rapidly advanced as a key component of artificial intelligence-generated content, enabling the generation of high-quality, highly realistic speech for diverse applications. This development increases the…

声音 · 计算机科学 2025-05-06 Yong Ren , Jiangyan Yi , Tao Wang , Jianhua Tao , Zheng Lian , Zhengqi Wen , Chenxing Li , Ruibo Fu , Ye Bai , Xiaohui Zhang

While Audio Large Models (ALMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaussian noise or simplistic single-source interference, failing…

Deepfakes and manipulated media are becoming a prominent threat due to the recent advances in realistic image and video synthesis techniques. There have been several attempts at combating Deepfakes using machine learning classifiers.…

计算机视觉与模式识别 · 计算机科学 2022-04-06 Paarth Neekhara , Shehzeen Hussain , Xinqiao Zhang , Ke Huang , Julian McAuley , Farinaz Koushanfar