Deepfake Detection Reading Group

We meet every two weeks to discuss papers on deepfake detection. Each session features either a paper someone found interesting or an invited speaker presenting their own work (invited talks are denoted by below). Sessions are informal, we often dive straight into the paper together, so as a speaker there is little to prepare. If you'd like to attend or present, feel free to join our mailing list.

When
Fridays (odd weeks)
3:00 p.m. EET
Google Calendar
Mailing list
Google Group
Notes & resources
Wiki

Season 3 · 2026-01 – …

Date: 2026-05-22 · Speaker: Andu
Boldisor, Dragos-Alexandru, et al. Investigating self-supervised representations for audio-visual deepfake detection. CVPR, 2026.
Date: 2026-05-08 · Speaker: Teo
Mahapatra, Aurosweta, et al. ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks. arXiv:2604.13229v1 (2026).
Date: 2026-04-24 · Speaker: Jonas
Höltervennhoff, Sandra, et al. "That's another doom I haven't thought about": A User Study on AI Labels as a Safeguard Against Image-Based Misinformation. CHI, 2025.
Date: 2026-03-27 · Speaker: Viola
Negroni, Viola, et al. Leveraging mixture of experts for improved speech deepfake detection. ICASSP, 2025.
Negroni, Viola, et al. Attention-based mixture of experts for robust speech deepfake detection. WIFS, 2025.
Date: 2026-03-13 · Speaker: Ștefan
Wang, Chi, et al. Low-rank orthogonal subspace intervention for generalizable face forgery detection. arXiv:2601.11915 (2026).
Yan, Zhiyuan, et al. Orthogonal subspace decomposition for generalizable AI-generated image detection. ICML, 2025.
Date: 2026-02-27 · Speaker: Alin
Croitoru, Florinel-Alin, et al. MAVOS-DD: Multilingual audio-video open-set deepfake detection benchmark. arXiv:2505.11109 (2025).
Date: 2026-02-13 · Speaker: Andu
Xiong, Wuti, Guoying Zhao, and Xiaobai Li. Exemplar-free incremental deepfake detection. ECAI, 2025.
Date: 2026-01-30 · Speaker: Christos
Koutlis, Christos, and Symeon Papadopoulos. AuViRe: Audio-visual speech representation reconstruction for deepfake temporal localization. WACV, 2026.

Season 2 · 2024-10 – 2025-06

Date: 2025-06-20 · Speaker: Dan
Dufour, Nicholas, et al. AMMeBa: A large-scale survey and dataset of media-based misinformation in-the-wild. arXiv:2405.11697 (2024).
Date: 2025-06-06 · Speaker: David
Combei, David, et al. Unmasking real-world audio deepfakes: a data-centric approach. Interspeech, 2025.
Stan, Adriana, et al. TADA: Training-free attribution and out-of-domain detection of audio deepfakes. Interspeech, 2025.
Date: 2025-05-23 · Speaker: Ioana
Zhang, Zirui, et al. I can hear you: Selective robust training for deepfake audio detection. ICLR, 2025.
Date: 2025-05-09 · Speaker: Teo
Zhu, Yi, et al. SLIM: Style-linguistics mismatch model for generalized audio deepfake detection. NeurIPS, 2024.
Date: 2025-03-14 · Speaker: Dimitris
Karageorgiou, Dimitrios, et al. Any-resolution AI-generated image detection by spectral learning. CVPR, 2025.
Date: 2025-02-28 · Speaker: Andu
Choi, Jongwook, et al. Exploiting style latent flows for generalizing deepfake video detection. CVPR, 2024.
Date: 2025-01-31 · Speaker: Xi
Wang, Xi, and Vicky Kalogeiton. Your diffusion model is an implicit synthetic image detector. ECCVW, 2024.
Date: 2025-01-14 · Speaker: Eli
Lian, Jingchun, et al. A large-scale interpretable multi-modality benchmark for facial image forgery localization. arXiv:2412.19685 (2024).
Date: 2024-12-20 · Speaker: Christos
Koutlis, Christos, and Symeon Papadopoulos. DiMoDif: Discourse modality-information differentiation for audio-visual deepfake detection and localization. arXiv:2411.10193 (2024).
Date: 2024-12-06 · Speaker: Ștefan
Qiao, Tong, et al. Fully unsupervised deepfake video detection via enhanced contrastive learning. PAMI (2024).
Date: 2024-11-22 · Speaker: Andu
Sarkar, Ayush, et al. Shadows don't lie and lines can't bend! Generative models don't know projective geometry... for now. CVPR, 2024.
Date: 2024-11-08 · Speaker: Dan
Rajan, Anirudh Sundara, et al. On the effectiveness of dataset alignment for fake image detection. arXiv:2410.11835 (2024).
Date: 2024-10-25 · Speaker: David
Azeemi, Abdul Hameed, Ihsan Ayyub Qazi, and Agha Ali Raza. Self-supervised dataset pruning for efficient training in audio anti-spoofing. Interspeech, 2023.
Date: 2024-10-11 · Speaker: Eli
Oorloff, Trevine, et al. AVFF: Audio-visual feature fusion for video deepfake detection. CVPR, 2024.

Season 1 · 2023-10 – 2024-06

Date: 2024-06-28 · Speaker: Ștefan
Chen, Baoying, et al. DRCT: Diffusion reconstruction contrastive training towards universal detection of diffusion generated images. ICML, 2024.
Date: 2024-06-07 · Speaker: Christos
Chugh, Komal, et al. Not made for each other — audio-visual dissonance-based deepfake detection and localization. ACMM, 2020.
Date: 2024-05-22 · Speaker: Dan
Boyd, Aidan, et al. The value of AI guidance in human examination of synthetically-generated faces. AAAI, 2023.
Date: 2024-05-08 · Speaker: Adriana
Yu, Zhiyuan, Shixuan Zhai, and Ning Zhang. AntiFake: Using adversarial audio to prevent unauthorized speech synthesis. ACM CCS, 2023.
Date: 2024-04-12 · Speaker: Spiros
Jia, Shan, Xin Li, and Siwei Lyu. Model attribution of face-swap deepfake videos. ICIP, 2022.
Date: 2024-03-29 · Speaker: Gabi
Müller, Nicolas M., Franziska Dieckmann, and Jennifer Williams. Attacker attribution of audio deepfakes. Interspeech, 2022.
Date: 2024-03-15 · Speaker: Eli
Zhang, Yue, et al. Common sense reasoning for deep fake detection. arXiv:2402.00126 (2024).
Date: 2024-02-02 · Speaker: Ștefan
Nguyen, Dat, et al. LAA-Net: Localized artifact attention network for high-quality deepfakes detection. arXiv:2401.13856 (2024).
Date: 2024-01-19 · Speaker: Octav
Cai, Zexin, and Ming Li. Integrating frame-level boundary detection and deepfake detection for locating manipulated regions in partially spoofed audio forgery attacks. Computer Speech & Language 85 (2024).
Date: 2023-12-08 · Speaker: Adriana
Cai, Zhixi, et al. AV-Deepfake1M: A large-scale LLM-driven audio-visual deepfake dataset. arXiv:2311.15308 (2023).
Date: 2023-11-24 · Speaker: Dan
Feng, Chao, Ziyang Chen, and Andrew Owens. Self-supervised video forensics by audio-visual anomaly detection. CVPR, 2023.
Date: 2023-11-10 · Speaker: Ema
Liang, Jiahao, et al. Exploring disentangled content information for face forgery detection. ECCV, 2022.
Date: 2023-10-27 · Speaker: Eli
Yan, Zhiyuan, et al. UCF: Uncovering common features for generalizable deepfake detection. ICCV, 2023.