SL
Siwei Lyu
cs.CVcs.LGcs.AIcs.CRcs.CLstat.MLcs.MMcs.SDeess.IVeess.AS
On Valency
published · living versionsW_raacqkk3·v1 · currentpublished
Partially Edited Audio: Generation, Defense, and Open Problems
with Lin Zhang, You Zhang, Nicholas Evans, Xin Wang +5
1 version
Preprints & journals
143 papers in the corpus · 2004–2026Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection.42335052 · Cui, Xinjie, Li, Yuezun, Zhu, Delong et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):13354-13369
DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling2609.34237v1 · Zheyuan Zhan, Can Wang, Jiawei Chen et al.2026 · 0 citationsarXiv
AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces2609.34854v1 · Zhijie Deng, Ling Li, Junhao Ji et al.2026 · 0 citationsarXiv
A survey of AI-generated voices and their detection2608.15411v1 · Chengzhe Sun, Tianle Yang, Siwei Lyu2026 · 0 citationsarXiv
Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editing2606.14125v1 · Zheyuan Zhan, Hongchen Li, Can Wang et al.2026 · 0 citationsarXiv
Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation2603.21078v1 · Tianle Yang, Chengzhe Sun, Phil Rose et al.2026 · 1 citationTianle Yang, Chengzhe Sun, Phil Rose, Cassandra L. Jacobs, and Siwei Lyu. 2026. Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation. Computer Speech & Language 100: 101983
BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation2603.02816v2 · Zihao Zhu, Ruotong Wang, Siwei Lyu et al.2026 · 0 citationsarXiv
Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework2602.03268v1 · Guanzong Wu, Zihao Zhu, Siwei Lyu et al.2026 · 0 citationsarXiv
Forensic deepfake audio detection using segmental speech features.41385900 · Yang, Tianle, Sun, Chengzhe, Lyu, Siwei et al.2026 · 13 citationsForensic science international. 2026;379:112768
Framing digital inauthenticity: Comparing user detection of AI-generated faces to messaged-based scam methods.41349270 · Sarno, Dawn M, Solorio, John, Ballar, Shea et al.2026 · 1 citationActa psychologica. 2026;262:105995
CrossDF: improving cross-domain deepfake detection with deep information decomposition.41346569 · Yang, Shanmin, Guo, Hui, Hu, Shu et al.2025 · 15 citationsFrontiers in big data. 2025;8:1669488
A self-learning multimodal approach for fake news detection.41280884 · Chen, Hao, Yu, Yue, Guo, Hui et al.2025 · 11 citationsFrontiers in artificial intelligence. 2025;8:1665798
RL-I2IT: Image-to-image translation with deep reinforcement learning.41218403 · Hu, Jing, Luo, Ziwei, Feng, Chengming et al.2026 · 3 citationsNeural networks : the official journal of the International Neural Network Society. 2026;195:108264
PIA: Deepfake Detection Using Phoneme-Temporal and Identity-Dynamic Analysis2510.14241v1 · Soumyya Kanti Datta, Tanvi Ranga, Chengzhe Sun et al.2025 · 3 citationsarXiv
AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models2509.24269v1 · Zihao Zhu, Xinyu Wu, Gehan Hu et al.2025 · 0 citationsarXiv
Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics2507.18015v1 · Yuezun Li, Delong Zhu, Xinjie Cui et al.2025 · 0 citationsarXiv
Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative Models2506.10177v3 · Defang Chen, Zhenyu Zhou, Can Wang et al.2025 · 1 citationJ. Stat. Mech. (2025) 124002
Tamper-evident Image using JPEG Fixed Points2504.17594v1 · Zhaofeng Si, Siwei Lyu2025 · 1 citationarXiv
Detecting Lip-Syncing Deepfakes: Vision Temporal Transformer for Analyzing Mouth Inconsistencies2504.01470v1 · Soumyya Kanti Datta, Shan Jia, Siwei Lyu2025 · 0 citationsarXiv
HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Models2503.19157v1 · Mingzhen Huang, Fu-Jen Chu, Bugra Tekin et al.2025 · 5 citationsarXiv
Your Text Encoder Can Be An Object-Level Watermarking Controller2503.11945v1 · Naresh Kumar Devulapally, Mingzhen Huang, Vishal Asnani et al.2025 · 1 citationarXiv
Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges2502.19716v3 · Qijie Xu, Can Wang, Jiawei Chen et al.2025 · 0 citationsarXiv
DICE: Distilling Classifier-Free Guidance into Text Embeddings2502.03726v3 · Zhenyu Zhou, Defang Chen, Can Wang et al.2025 · 0 citationsarXiv
HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing2412.05685v1 · Zihao Zhu, Hongbao Zhang, Guanzong Wu et al.2024 · 0 citationsarXiv
Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection2412.01101v2 · Delong Zhu, Yuezun Li, Baoyuan Wu et al.2024 · 6 citationsarXiv
X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection2410.06126v4 · Yize Chen, Zhiyuan Yan, Guangliang Cheng et al.2024 · 5 citationsarXiv
Conditional Image Synthesis with Diffusion Models: A Survey2409.19365v3 · Zheyuan Zhan, Defang Chen, Jian-Ping Mei et al.2024 · 3 citationsarXiv
Semantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach2408.16305v2 · Mian Zou, Baosheng Yu, Yibing Zhan et al.2024 · 14 citationsarXiv
Knowledge Distillation with Refined Logits2408.07703v3 · Wujie Sun, Defang Chen, Siwei Lyu et al.2024 · 14 citationsarXiv
Dense Feature Interaction Network for Image Inpainting Localization2408.02191v2 · Ye Yao, Tingfeng Han, Shan Jia et al.2024 · 17 citationsarXiv
Vision-Language Model Based Handwriting Verification2407.21788v1 · Mihir Chauhan, Abhishek Satbhai, Mohammad Abuzar Hashemi et al.2024 · 3 citationsarXiv
ParallelEdits: Efficient Multi-object Image Editing2406.00985v4 · Mingzhen Huang, Jialing Cai, Shan Jia et al.2024 · 0 citationsarXiv
Self-Supervised Learning Based Handwriting Verification2405.18320v2 · Mihir Chauhan, Mohammad Abuzar Hashemi, Abhishek Satbhai et al.2024 · 3 citationsarXiv
On the Trajectory Regularity of ODE-based Diffusion Sampling2405.11326v1 · Defang Chen, Zhenyu Zhou, Can Wang et al.2024 · 0 citationsarXiv
Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method2405.08487v3 · Mian Zou, Baosheng Yu, Yibing Zhan et al.2024 · 9 citationsarXiv
Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection2404.19171v1 · Cai Yu, Shan Jia, Xiaomeng Fu et al.2024 · 7 citationsarXiv
Exposing Text-Image Inconsistency Using Diffusion Models2404.18033v1 · Mingzhen Huang, Shan Jia, Zhou Zhou et al.2024 · 2 citationsarXiv
DeepFake-O-Meter v2.0: An Open Platform for DeepFake Detection2404.13146v2 · Yan Ju, Chengzhe Sun, Shan Jia et al.2024 · 12 citationsarXiv
Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics2403.14077v4 · Shan Jia, Reilin Lyu, Kangran Zhao et al.2024 · 57 citationsarXiv
Exposing Lip-syncing Deepfakes from Mouth Inconsistencies2401.10113v2 · Soumyya Kanti Datta, Shan Jia, Siwei Lyu2024 · 23 citationsarXiv
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection2311.11278v2 · Zhiyuan Yan, Yuhao Luo, Siwei Lyu et al.2023 · 166 citationsarXiv
UMedNeRF: Uncertainty-aware Single View Volumetric Rendering for Medical Neural Radiance Fields2311.05836v7 · Jing Hu, Qinrui Fan, Shu Hu et al.2023 · 19 citationsarXiv
ExS-GAN: Synthesizing Anti-Forensics Images via Extra Supervised GAN.36264736 · Ding, Feng, Shen, Zhangyi, Zhu, Guopu et al.2023 · 42 citationsIEEE transactions on cybernetics. 2023;53(11):7162-7173
Efficient State Estimation with Constrained Rao-Blackwellized Particle Filter2310.04637v1 · Shuai Li, Siwei Lyu, Jeff Trinkle2023 · 1 citationarXiv
Integrating Audio-Visual Features for Multimodal Deepfake Detection2310.03827v1 · Sneha Muppalla, Shan Jia, Siwei Lyu2023 · 46 citationsarXiv
Rank-Based Decomposable Losses in Machine Learning: A Survey.37459267 · Hu, Shu, Wang, Xin, Lyu, Siwei2023 · 29 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(11):13599-13620
Controlling Neural Style Transfer with Deep Reinforcement Learning2310.00405v1 · Chengming Feng, Jing Hu, Xin Wang et al.2023 · 3 citationsarXiv
Outlier Robust Adversarial Training2309.05145v1 · Shu Hu, Zhenhuan Yang, Xin Wang et al.2023 · 5 citationsarXiv
Language-guided Human Motion Synthesis with Atomic Actions2308.09611v1 · Yuanhao Zhai, Mingzhen Huang, Tianyu Luan et al.2023 · 12 citationsarXiv
COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection2308.01520v2 · Cong Zhang, Honggang Qi, Shuhui Wang et al.2023 · 15 citationsarXiv
Career total: 307 works. 143 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.