Related papers: ProtoExplorer: Interpretable Forensic Analysis of …

Deeplearning has been used to solve complex problems in various domains. As it advances, it also creates applications which become a major threat to our privacy, security and even to our Democracy. Such an application which is being…

The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors,…

The misuse of deepfake technology by malicious actors poses a potential threat to nations, societies, and individuals. However, existing methods for detecting deepfakes primarily focus on uncompressed videos, such as noise characteristics,…

One of the most pressing challenges for the detection of face-manipulated videos is generalising to forgery methods not seen during training while remaining effective under common corruptions such as compression. In this paper, we examine…

Existing deepfake detection methods often exhibit bias, lack transparency, and fail to capture temporal information, leading to biased decisions and unreliable results across different demographic groups. In this paper, we propose a…

Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we…

The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the predictive performance of the model, or produce…

Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real…

The proliferation of synthetic images generated by advanced AI models poses significant challenges in identifying and understanding manipulated visual content. Current fake image detection methods predominantly rely on binary classification…

We present ProtoConcepts, a method for interpretable image classification combining deep learning and case-based reasoning using prototypical parts. Existing work in prototype-based image classification uses a ``this looks like that''…

Prototypical part network (ProtoPNet) has drawn wide attention and boosted many follow-up studies due to its self-explanatory property for explainable artificial intelligence (XAI). However, when directly applying ProtoPNet on vision…

Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate model predictions with…

Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degrade visual information and increase prediction uncertainty. Existing methods either…

Deepfake technology is widely used, which has led to serious worries about the authenticity of digital media, making the need for trustworthy deepfake face recognition techniques more urgent than ever. This study employs a…

As machine learning (ML) models and datasets increase in complexity, the demand for methods that enhance explainability and interpretability becomes paramount. Prototypes, by encapsulating essential characteristics within data, offer…

Previous deepfake detection methods mostly depend on low-level textural features vulnerable to perturbations and fall short of detecting unseen forgery methods. In contrast, high-level semantic features are less susceptible to perturbations…

Recent advancements in deep learning generative models have raised concerns as they can create highly convincing counterfeit images and videos. This poses a threat to people's integrity and can lead to social instability. To address this…

Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous systems, where models must provide not only accurate…

This demonstration paper presents $\mathbf{LayLens}$, a tool aimed to make deepfake understanding easier for users of all educational backgrounds. While prior works often rely on outputs containing technical jargon, LayLens bridges the gap…

We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accuracy comparable to baseline methods, we adapt the mechanism of…