Cover Image

The Deepfake Detective: Interpreting Neural Forensics Through Sparse Features and Manifolds

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sahoo, Subramanyam, Junkin, Jared
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems
by: Sahoo, Subramanyam, et al.
Published: (2025)

Fair and Interpretable Deepfake Detection in Videos
by: Yoshii, Akihito, et al.
Published: (2025)

Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection
by: Yang, Yang, et al.
Published: (2022)

ForensicFlow: A Tri-Modal Adaptive Network for Robust Deepfake Detection
by: Romani, Mohammad
Published: (2025)

Nearly Solved? Robust Deepfake Detection Requires More than Visual Forensics
by: Levy, Guy, et al.
Published: (2024)

Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold
by: Jin, Yinzhu, et al.
Published: (2024)

Deepfake Detection of Face Images based on a Convolutional Neural Network
by: Kroiß, Lukas, et al.
Published: (2025)

Forensic Study of Paintings Through the Comparison of Fabrics
by: Murillo-Fuentes, Juan José, et al.
Published: (2025)

Conditional Uncertainty-Aware Political Deepfake Detection with Stochastic Convolutional Neural Networks
by: Gardoş, Rafael-Petruţ
Published: (2026)

Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning
by: Khan, Sarwar
Published: (2024)

Age-Diverse Deepfake Dataset: Bridging the Age Gap in Deepfake Detection
by: Joshi, Unisha
Published: (2025)

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
by: Zi, Bojia, et al.
Published: (2021)

Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection
by: Shen, Qihao, et al.
Published: (2026)

Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks
by: Romeo, Lanzino, et al.
Published: (2024)

Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
by: Hu, Xuran, et al.
Published: (2024)

Keypoint Aware Masked Image Modelling
by: Krishna, Madhava, et al.
Published: (2024)

Audio Deepfake Detection with Half-Truth Localisation Using Cross-Attentive Feature Fusion
by: Sutharya, S., et al.
Published: (2026)

Flows and Diffusions on the Neural Manifold
by: Saragih, Daniel, et al.
Published: (2025)

Enhancing Neural Network Interpretability Through Conductance-Based Information Plane Analysis
by: Dabounou, Jaouad, et al.
Published: (2024)

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
by: Kulkarni, Akshay, et al.
Published: (2025)

Preserving Fairness Generalization in Deepfake Detection
by: Lin, Li, et al.
Published: (2024)

Conditional Consistency Guided Image Translation and Enhancement
by: Bhagat, Amil, et al.
Published: (2025)

Comparative Analysis of Deepfake Detection Models: New Approaches and Perspectives
by: Batista, Matheus Martins
Published: (2025)

Enhancing Interpretability of Sparse Latent Representations with Class Information
by: Abiz, Farshad Sangari, et al.
Published: (2025)

Sparse Autoencoders for Interpretable Medical Image Representation Learning
by: Wesp, Philipp, et al.
Published: (2026)

PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
by: Nguyen, Tuan, et al.
Published: (2025)

Interpretable Dynamic Graph Neural Networks for Small Occluded Object Detection and Tracking
by: Soudeep, Shahriar, et al.
Published: (2024)

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
by: Thasarathan, Harrish, et al.
Published: (2025)

CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models
by: He, Zhenghao, et al.
Published: (2026)

Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection
by: Lei, Zhanhe, et al.
Published: (2026)

Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection
by: Wu, Yingwen, et al.
Published: (2024)

Analyzing Fairness in Deepfake Detection With Massively Annotated Databases
by: Xu, Ying, et al.
Published: (2022)

Sparse Modelling for Feature Learning in High Dimensional Data
by: Neelam, Harish, et al.
Published: (2024)

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
by: Bhalla, Usha, et al.
Published: (2024)

Boosting Weak Positives for Text Based Person Search
by: Modi, Akshay, et al.
Published: (2025)

ViGText: Deepfake Image Detection with Vision-Language Model Explanations and Graph Neural Networks
by: ALBarqawi, Ahmad, et al.
Published: (2025)

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
by: Amini, Sajjad, et al.
Published: (2024)

Explainable Deepfake Video Detection using Convolutional Neural Network and CapsuleNet
by: Ishrak, Gazi Hasin, et al.
Published: (2024)

Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection
by: Liao, Jianfeng, et al.
Published: (2026)

Face Deepfakes -- A Comprehensive Review
by: Fernando, Tharindu, et al.
Published: (2025)