彭勃，博士，副研究员， 2018 年至今在中科院自动化所工作。在AIGC内容合成与治理、图像内容取证与安全、深度伪造对抗与攻防等领域有丰富的研究经验。主持科技创新2030— 新一代人工智能重大项目课题、国家自然科学基金面上项目、中国科协青年托举项目、北京市自然科学基金面上项目、华为MindSpore学术奖励基金等十余项。在 IEEE TPAMI、TIFS、TCSVT、TMM、CVPR、 AAAI、ACM MM等重要国际期刊和会议上发表论文60余篇，获发明专利授权19项，曾获中国发明协会发明创业奖创新奖一等奖、中国图象图形学学会技术发明奖二等奖等、中国模式识别与计算机视觉大会等会议最佳论文奖等。目前是中国图像图形学会数字媒体取证与安全专委会委员、生物特征识别专委会委员、北京图象图形学会青工委委员、IEEE Beijing Biometrics Council Chapter Secretary。

081104-模式识别与智能系统
081002-信号与信息处理
083900-网络空间安全

图像取证、视觉内容生成与合成、视觉质量评估
生理信号感知、弱信号增强、信息理论
信息隐藏、图像水印

对于搞清楚一件事情具有纯粹的兴趣（“格物致知”）

2020-11--中国科学院自动化研究所   副研究员
2018-07--2020-10   中国科学院自动化研究所   助理研究员
2013-09--2018-06   中国科学院自动化研究所   工学博士
2009-09--2013-06   北京航空航天大学   工学学士

   

2020-11~现在, 中国科学院自动化研究所, 副研究员
2018-07~2020-10,中国科学院自动化研究所, 助理研究员

2025-04-01-今,中国图象图形学学会生物特征识别专业委员会委员,
2021-01-01-今,EEE Beijing Biometrics Council Chapter Secretary, 秘书长
2018-12-31-今,中国图象图形学学会数字媒体取证与安全专业委员会委员,

   

“人工智能安全与对抗”，国科大研究生专业课，春季学期（2024年-）

“人工智能安全与伦理”，中关村学院研究生专业课，春季学期（2026年-）

1. 2025 Chinese Conference on Pattern Recognition and Computer Vision (PRCV) Best paper award & CCF outstanding paper award
2. Chinese Conference on Biometrics (CCBR) Best Paper Honorable Mention Award, 其他, 2024
3. 全国大数据与计算智能挑战赛--“基于对抗场景下重要目标人脸深度伪造视频检测”赛题一等奖, 一等奖, 专项, 2024
4. 中国发明协会发明创业奖创新奖 一等奖, 一等奖, 专项, 2022
5. 第二届广播电视和网络视听人工智能应用创新大赛 一等奖, 一等奖, 专项, 2022
6. 第七届中国科协青年人才托举工程, 专项, 2021
7. 2021年度中国图象图形学学会技术发明奖 二等奖, 二等奖, 专项, 2021

1. 彭勃，张晓宇，董晶，王伟，杨琛. 反事实解释生成方法及装置，专利号：ZL 2025 1 0090708.9 ，授权公告日：2025.4.29，授权公告号： CN 119540659 B ，专 利 申 请 日： 2025年01月21日
2. 董晶,王伟,彭勃,王建文,吕月明,江玥,杨嵩林. 基于跨模态风格学习的图像生成方法及装置, 申请号：CN202311265075.8, 申请日期：2023-09-27，专利号：ZL 2023 1 1265075.8，授权公告日：2024.12.13
3. 王伟,董晶,彭勃,杨嵩林,吕月明. 说话人视频的编辑帧生成方法、装置、电子设备及介质, 申请号：CN202311418899.4，申请日期：2023-10-30，专利号：ZL 2023 1 1418899.4，授权公告日：2024.1.2
4. 彭勃，董晶，王伟，王建文. 人脸鉴伪取证方法及装置、电子设备及存储介质，申请号: CN202211076090.3，申请日期: 2022.9.5, 授权公告日: 2023.3.28，专利号: ZL 2022 1 1076090.3
5. 董晶，王伟，彭勃，王丽，王建文，项伟，宋宗泽. 基于生成模型的人脸对抗口罩样本生成方法和系统，申请号: CN202210823234.0，申请日期: 2022.7.14，授权公告日: 2022.10.28，专利号: ZL 2022 1 0823234.0
6. 王伟，董晶，彭勃，杨嵩林，王建文. 人脸活体检测对抗鲁棒性的评估方法及装置, 申请号：CN202210165316.0，申请日期：2022.2.23, 授权公告日：2022.5.24，专利号： ZL 2022 1 0165316.0
7. 董晶，王伟，彭勃，赵冰浩，马天翔，宋宗泽. 图像生成方法、装置、电子设备及存储介质，申请号：CN202210063293.2，申请日期：2022.1.20，授权公告日：2022.4.12，专利号： ZL 2022 1 0063293.2
8. 董晶，王伟，彭勃，何子文，项伟，谭铁牛. 基于视觉对抗重构的DeepFake防御方法和系统, 申请号：CN202210002592.5，申请日期：2022.1.5，授权公告日：2022.3.25，专利号： ZL 2022 1 0002592.5
9. 董晶，王伟，彭勃，何子文，谭铁牛. 对抗样本图像的确定方法、装置、电子设备及存储介质, 申请号：CN202110875691.X 申请日期：2021.7.30，授权公告日：2021.11.9，专利号： ZL 2021 1 0875691.X
10. 董晶，王伟，彭勃，王建文，项伟，樊红兴. 抗JPEG压缩的伪造图像检测方法, 申请号：CN202110665199.X 申请日期：2021.6.16 授权公告日：，专利号： ZL 2021 1 0665199.X
11. 董晶，王伟，彭勃，管伟楠，谭铁牛. 基于人脸三维形状的换脸伪造检测方法、系统及设备，申请日期：2021.3.31,申请号：PCT/CN2021/084421, 授权公告日：2021.12.14，专利号：ZL 2021 1 0219838.X
12. 董晶，王伟，彭勃，王建文. 基于三维人脸分解的换脸与重演方法及装置, 申请日期：2021.8.2，授权公告日：2021.10.15，专利号：ZL 2021 1 0882708.4，已授权、已转化（中科闻歌）。
13. 王伟，董晶，彭勃，李东泽，马天翔. 一种基于操控解耦身份表示的人脸匿名方法, 申请号：CN202110556372.2 申请日期：2021.5.21 授权公告日：2021.08.10，专利号： ZL 2021 1 0556372.2
14. 董晶，王伟，彭勃，卞明运. 基于多尺度深度特征融合的人脸深度篡改图像的检测方法，授权公告日：2021.8.31，专利号：ZL 2020 1 0348237.4
15. 谭铁牛，董晶，王伟，彭勃. 基于视频的非接触式脉搏实时估计方法及设备，授权公告日：2020.12.15，专利号：ZL 2018 1 1362231.1
16. 谭铁牛，董晶，王伟，彭勃. 图像篡改取证方法及装置，PCT发明专利，PCT/CN2017/076106，授权公告日：2020.02.28，专利号：ZL 2017 1 0137310.1
17. Tieniu Tan、Jing Dong、Wei Wang、Bo Peng，IMAGE TAMPERING FORENSICS METHOD AND APPARATUS,申请号：16336918，申请日期： 2017.03.09，授权公告日：2020.3.24，专利号：US 10,600,238 B2
18. 谭铁牛，董晶，王伟，彭勃. 基于透视失真特性的人脸图像鉴伪方法、存储、处理设备，PCT发明专利，PCT/CN2017/089685，授权公告日：2020.02.28，专利号：ZL 2017 1 0484342.9
19. Tieniu Tan、Jing Dong、Wei Wang、Bo Peng，PERSPECTIVE DISTORTION CHARACTERISTIC BASED FACIAL IMAGE AUTHENTICATION METHOD AND STORAGE AND PROCESSING DEVICE THEREOF, 申请号：16488600，申请日期： 2017.06.23，授权公告日：2020.05.12，专利号：US 10,650,260 B2

   

（1） Encyclopedia of Cryptography, Security and Privacy, Springer, 2025-01, 第 其他 作者

期刊论文

1. Bo Peng, Zichuan Wang, Sheng Yu, Xiaochuan Jin, Wei Wang, Jing Dong, "DREAM: A Benchmark Study for Deepfake photoREalism AssessMent", in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. , no. 01, pp. 1-16, PrePrints 5555, doi: 10.1109/TPAMI.2026.3663547.
2. Bo Peng, Hongxing Fan, Wei Wang, Jing Dong and Siwei Lyu, "A Unified Framework for High Fidelity Face Swap and Expression Reenactment," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 6, pp. 3673-3684, Jun. 2022.
3. Bo Peng, Wei Wang, Jing Dong, Tieniu Tan, "Learning Pose-invariant 3D Object Reconstruction from Single-view Images", Neurocomputing, vol. 423, pp. 407-418, Jan. 2021.
4. Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, "Image Forensics Based on Planar Contact Constraints of 3D Objects," IEEE Transactions on Information Forensics and Security, vol. 13, no. 2, pp. 377-392, Feb. 2018.
5. Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, "Optimized 3D Lighting Environment Estimation for Image Forgery Detection," IEEE Transactions on Information Forensics and Security, vol. 12, no. 2, pp. 479-494, Feb. 2017.
6. Zheling Meng, Bo Peng, Xiaochuan Jin, Yue Jiang, Wei Wang, Jing Dong, Tieniu Tan, "Dark Miner: Towards combating residuals in concept erasure for text-to-image diffusion models", Neurocomputing, 2026.
7. Weinan Guan, Wei Wang, Bo Peng, Ziwen He, Jing Dong, Haonan Cheng, "Noise-Informed Diffusion-Generated Image Detection with Anomaly Attention", IEEE Transactions on Information Forensics & Security (TIFS), 2025.
8. Yue Jiang, Yueming Lyu, Bo Peng, Wei Wang, Jing Dong, "CMSL: Cross-Modal Style Learning for Few-shot Image Generation", Machine Intelligence Research (MIR), 2025, 1-17.
9. Zheling Meng, Bo Peng, Jing Dong, “Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space”, IEEE Transactions on Multimedia (TMM), 2025.
10. Zheling Meng, Bo Peng, Jing Dong, Tieniu Tan, Haonan Cheng, "Artifact Feature Purification for Cross-domain Detection of AI-generated Images", Computer Vision and Image Understanding (CVIU), 2024.
11. Weinan Guan, Wei Wang, Jing Dong, Bo Peng, "Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization", IEEE Transactions on Information Forensics & Security (TIFS), 2024.
12. Yueming Lyu, Yue Jiang, Bo Peng, Jing Dong, "InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 34, no. 4, pp. 2070-2082, April 2024.
13. Yueming Lyu, Yue Jiang, Ziwen He, Bo Peng, Yunfan Liu, Jing Dong, "3D-Aware Adversarial Makeup Generation for Facial Privacy Protection", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Nov. 2023, pp. 13438-13453, vol. 45, 2023.
14. Yueming Lyu, Peibin Chen, Jingna Sun, Bo Peng, Xu Wang, Jing Dong, "DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis", IEEE Transactions on Multimedia (TMM), vol. 26, pp. 1969-1982, 2024.
15. 张芃芃，彭勃*，董晶，程皓楠，基于大语言模型与视觉语言模型的多模态事实核查[J].中国传媒大学学报(自然科学版),2024,31(04):30-37+54.
16. 张芃芃, 宋宗泽, 彭勃*, 董晶. 面向人脸深度伪造检测模型的校准性评测[J]. 网络空间安全科学学报, 2023, 1(3): 97-106
17. 张时润,彭勃,王伟,董晶.基于空洞卷积和注意力机制的深度伪造检测[J].现代电子技术,2022,45(05):42-48.
18. 卞明运,彭勃,王伟,董晶.基于空洞卷积的低质量人脸深度伪造图片检测[J].现代电子技术,2021,44(06):133-138.

会议论文

1. Bo Peng, Xianyun Sun, Caiyong Wang, Wei Wang, Jing Dong, Zhenan Sun, et al., "DFGC-VRA: DeepFake Game Competition on Visual Realism Assessment", 2023 IEEE International Joint Conference on Biometrics (IJCB).
2. Bo Peng, Siwei Lyu, Wei Wang, Jing Dong, "Counterfactual Image Enhancement for Explanation of Face Swap Deepfakes", Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2022.
3. Bo Peng, Wei Xiang, Yue Jiang, Wei Wang, Jing Dong, Zhenan Sun, Zhen Lei, Siwei Lyu, "DFGC 2022: The Second DeepFake Game Competition", 2022 IEEE International Joint Conference on Biometrics (IJCB)
4. Bo Peng, Hongxing Fan, Wei Wang, Jing Dong, Yuezun Li, Siwei Lyu, Qi Li, Zhenan Sun, "DFGC 2021: A DeepFake Game Competition", 2021 IEEE International Joint Conference on Biometrics (IJCB), 2021, pp. 1-8, doi: 10.1109/IJCB52358.2021.9484387.
5. Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, "Position Determines Perspective: Investigating Perspective Distortion for Image Forensics of Faces", CVPR 2017 Media Forensics Workshop, Honolulu, Hawaii, 2017.7.26, pp. 1813-1821.
6. Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, "Automatic detection of 3D lighting inconsistencies via a facial landmark based morphable model", 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, 2016.9.25-2016.9.28, pp. 3932-3936.
7. Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, "Improved 3D lighting environment estimation for image forgery detection", 2015 IEEE International Workshop on Information Forensics and Security (WIFS), Rome, 2015.11.16-2015.11.19, pp. 1-6
8. Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, "Detection of computer generated faces in videos based on pulse signal", 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP), Chengdu, 2015.7.12-2015.7.15, pp. 841-845.
9. Zichuan Wang, Songlin Yang, Bo Peng*, Zhenchen Tang, Yang Li, Beibei Dong, Jing Dong, "Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination", Conference on Computer Vision and Pattern Recognition (CVPR) , hightlight paper, 2026.
10. Zhenchen Tang, Songlin Yang, Bo Peng*, Zichuan Wang, Jing Dong*, "Revisiting MLLM Based Image Quality Assessment: Errors and Remedy ", AAAI Conference on Artificial Intelligence (AAAI), 2026.
11. Zheling Meng, Bo Peng, Xiaochuan Jin, Yueming Lyu, Wei Wang, Jing Dong, Tieniu Tan, “Concept Corrector: Erase concepts on the fly for text-to-image diffusion models”, Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2025. (Best paper award, CCF outstanding paper award)
12. Shuhao Han, Haotian Fan, Fangyuan Kong, et al., "NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment", NTIRE Workshop and Challenges @ CVPR 2025.
13. Yue Jiang, Haokun Lin, Yang Bai, Bo Peng, Zhili Liu, Yueming Lyu, Yong Yang, Xingzheng, Jing Dong, “Image-level memorization detection via inversion-based inference perturbation”, International Conference on Learning Representations (ICLR), 2025.
14. Chen Yang, Bo Peng*, Jing Dong, Xiaoyu Zhang*, "Unveiling Deepfakes with Latent Diffusion Counterfactual Explanations", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025.
15. Yufei Zhang, Zheling Meng, Bo Peng, Jing Dong, Beilin Chu, Wei Wang, "Partial Reconstruction Error for Deepfake Detection", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP ), 2025.
16. Yufei Zhang, Bo Peng, Jing Dong, Weike You, Wei Wang, "Deepfake Video Detection Guided by Identity and Temporal Inconsistency", Chinese Conference on Biometrics (CCBR) 2024. （Best paper honorable mention award）
17. Zhenchen Tang, Zichuan Wang, Bo Peng*, Jing Dong, "CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP", International Conference on Pattern Recognition (ICPR), 2024.
18. Beibei Dong, Bo Peng, Jing Dong, "SPI2I: Structure Preserved Image-to-Image Translation with Diffusion Models", International Conference on Pattern Recognition (ICPR), 2024.
19. Ying Zhang, Yuezun Li, Bo Peng, Jiaran Zhou, Huiyu Zhou, Junyu Dong, “Mumpy: Multilateral Temporal-view Pyramid Transformer for Video Inpainting Detection”, British Machine Vision Conference (BMVC), 2024.
20. Yue Jiang, Yueming Lyu, Ziwen He, Bo Peng, Jing Dong, "Mitigating Social Biases in Text-to-Image Diffusion Models via Linguistic-Aligned Attention Guidance", ACM Multimedia, 2024.
21. Dongze Li, Kang Zhao, Wei Wang, Yifeng Ma, Bo Peng, Yingya Zhang, Jing Dong, "S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis", European Conference on Computer Vision (ECCV), 2024.
22. Weinan Guan, Wei Wang, Bo Peng, Jing Dong, Tieniu Tan, "ST-SBV: Spatial-Temporal Self-Blended Videos for Deepfake Detection", Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024.
23. Yang Li, Songlin Yang, Wei Wang, Ziwen He, Bo Peng, Jing Dong, “Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts”, IEEE Conference on Multimedia Expo 2024 (ICME).
24. Dongze Li, Kang Zhao, Wei Wang, Bo Peng, Yingya Zhang, Jing Dong, Tieniu Tan, "AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis", Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024.
25. Songlin Yang, Wei Wang, Yushi Lan, Xiangyu Fan, Bo Peng, Lei Yang, Jing Dong, "Learning Dense Correspondence for NeRF-Based Face Reenactment", Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024.
26. Songlin Yang, Wei Wang, Jun Ling, Bo Peng, Xu Tan, Jing Dong, "Context-Aware Talking-Head Video Editing", ACM MM, 2023.
27. Xianyun Sun, Beibei Dong, Caiyong Wang, Bo Peng*, Jing Dong, “Visual Realism Assessment for Face-Swap Videos”, International Conference on Image and Graphics (ICIG), 2023, Nanjing, China.
28. Songlin Yang, Wei Wang, Bo Peng, Jing Dong, "Designing a 3D-aware StyleNeRF Encoder for Face Editing", 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023.
29. Songlin Yang, Wei Wang, Chenye Xu, Ziwen He, Bo Peng, Jing Dong. "Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models." CVPR Workshop. 2023.
30. Weinan Guan, Wei Wang, Jing Dong, Bo Peng, Tieniu Tan, "Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation", 2022 IEEE International Joint Conference on Biometrics (IJCB).
31. Weinan Guan, Wei Wang, Jing Dong, Bo Peng, Tieniu Tan, "Robust Face-Swap Detection Based on 3D Facial Shape Information", CAAI International Conference on Artificial Intelligence (CICAI) 2022.
32. Weinan Guan, Ziwen He, Wei Wang, Jing Dong, Bo Peng, "Defending Against Deepfakes with Ensemble Adversarial Perturbation", ICPR2022, 2022
33. Binghao Zhao, Tianxiang Ma, Bo Peng, Jing Dong, "DesignerGAN: Sketch Your Own Photo", ICPR2022, 2022
34. Tianxiang Ma, Bo Peng, Wei Wang, Jing Dong, "MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation", 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13617-13626, 2021
35. Yueming Lyu, Jing Dong, Bo Peng, Wei Wang, Tieniu Tan, "SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer", ACM MM2021, 2021.
36. Xinsheng Xuan, Bo Peng, Wei Wang and Jing Dong, "On the Generalization of GAN Image Forensics", CCBR 2019, Zhuzhou, China.
37. Mingyun Bian, Bo Peng, Wei Wang and Jing Dong, "An Accurate LSTM Based Video Heart Rate Estimation Method", PRCV 2019, Xi'an, China.
38. Tianxiang Ma, Bo Peng, Wei Wang and Jing Dong, "Any-to-one Face Reenactment Based on Conditional Generative Adversarial Network", APSIPA 2019, Lanzhou, China, 2019.11
39. Kui Ye, Jing Dong, Wei Wang, Bo Peng, and Tieniu Tan “Feature Pyramid Deep Matching and Localization Network for Image Forensics”, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Honolulu, HI, USA, 2018, pp. 1796-1802.

   

1. 中国模式识别与计算机视觉大会（PRCV），讲习班报告，“生成合成人像的鉴别与质量评估 ”，2025.10.15
2. 中国模式识别与计算机视觉大会（PRCV）讲习班报告，“人脸伪造合成度分析研究”，2024.10.18
3. 组织 IEEE Beijing Biometrics Council Chapter Distinguished Lecturer Program活动，邀请 Prof. Mark Nixon做报告，2024.11.19.
4. 组织 IJCB'2023 学术比赛 DeepFake Game Competition on Visual Realism Assessment (DFGC-VRA)
5. 组织 IJCB'2022 学术比赛 DeepFake Game Competition (DFGC-2022)
6. 组织 IJCB'2021 学术比赛 DeepFake Game Competition (DFGC-2021)及在线比赛论坛
7. 组织 IEEE Beijing Section Biometrics Council Chapter Trustworthy Biometrics Webniar 活动第六期，Vitomir Štruc，2022.5.6，主持
8. CSIG中国媒体取证与安全大会（ChinaMFS）分论坛报告，“A Unified Framework for High Fidelity Face Swap and Expression Reenactment”，2021.11.13

1. 视觉深度合成质量评估研究, 负责人, 国家任务, 2023-01--2026-12
2. 基于伪造痕迹的可解释深度伪造鉴别研究, 负责人, 地方任务, 2023-01--2025-12