Related papers: The Deepfake Detective: Interpreting Neural Forens…

Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span manifolds that current linear methods cannot capture without post hoc analysis. This…

The combination of highly realistic voice cloning, along with visually compelling avatar, face-swap, or lip-sync deepfake video generation, makes it relatively easy to create a video of anyone saying anything. Today, such deepfake…

In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation…

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Image manipulation is rapidly evolving, allowing the creation of credible content that can be used to bend reality. Although the results of deepfake detectors are promising, deepfakes can be made even more complicated to detect through…

Deepfake detection research has largely converged on deep learning approaches that, despite strong benchmark performance, offer limited insight into what distinguishes real from manipulated facial behavior. This study presents an…

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

The classification of forged videos has been a challenge for the past few years. Deepfake classifiers can now reliably predict whether or not video frames have been tampered with. However, their performance is tied to both the dataset used…

Sparse Autoencoders (SAEs) have shown promise in improving the interpretability of neural network activations, but can learn features that are not features of the input, limiting their effectiveness. We propose \textsc{Mutual Feature…

In this paper we propose a novel human-centered approach for detecting forgery in face images, using dynamic prototypes as a form of visual explanations. Currently, most state-of-the-art deepfake detections are based on black-box models…

Part-level features are crucial for image understanding, but few studies focus on them because of the lack of fine-grained labels. Although unsupervised part discovery can eliminate the reliance on labels, most of them cannot maintain…

We address multimodal deepfake detection requiring both robustness and interpretability by proposing FakeHunter, a unified framework that combines memory guided retrieval, a structured Observation-Thought-Action reasoning loop, and adaptive…

This paper presents an innovative approach to dimensionality reduction and feature extraction in high-dimensional datasets, with a specific application focus on wood surface defect detection. The proposed framework integrates sparse…

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

The rise of deepfake technology brings forth new questions about the authenticity of various forms of media found online today. Videos and images generated by artificial intelligence (AI) have become increasingly more difficult to…

Deep convolutional neural networks have shown remarkable results on multiple detection tasks. Despite the significant progress, the performance of such detectors are often assessed in public benchmarks under non-realistic conditions.…

This paper shows that Masking the Deep hierarchical features is an efficient self-supervised method, denoted as MaskDeep. MaskDeep treats each patch in the representation space as an independent instance. We mask part of patches in the…

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many…

Deep Neural Networks (DNNs) are widely used for decision making in a myriad of critical applications, ranging from medical to societal and even judicial. Given the importance of these decisions, it is crucial for us to be able to interpret…

Recent advancements in text-to-speech and speech conversion technologies have enabled the creation of highly convincing synthetic speech. While these innovations offer numerous practical benefits, they also cause significant security…