Related papers: FBI: Fingerprinting models with Benign Inputs

Deep learning is extensively used in many areas of data mining as a black-box method with impressive results. However, understanding the core mechanism of how deep learning makes predictions is a relatively understudied problem. Here we…

A biometric recognition system can operate in two distinct modes: identification or verification. In the first mode, the system recognizes an individual by searching the enrolled templates of all the users for a match. In the second mode,…

Deep neural networks have achieved outstanding performance over various tasks, but they have a critical issue: over-confident predictions even for completely unknown samples. Many studies have been proposed to successfully filter out these…

Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the…

Machine learning algorithms are everywhere, ranging from simple data analysis and pattern recognition tools used across the sciences to complex systems that achieve super-human performance on various tasks. Ensuring that they are…

This paper investigates the challenging task of detecting backdoored text-to-image models under black-box settings and introduces a novel detection framework BlackMirror. Existing approaches typically rely on analyzing image-level…

Combinations of active automata learning, model-based testing and model checking have been successfully used in numerous applications, e.g., for spotting bugs in implementations of major network protocols and to support refactoring of…

Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small…

Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own…

Deep neural networks are highly vulnerable to adversarial examples, which are inputs with small, carefully crafted perturbations that cause misclassification -- making adversarial attacks a critical tool for evaluating robustness. Existing…

Deep learning is an important method for molecular design and exhibits considerable ability to predict molecular properties, including physicochemical, bioactive, and ADME/T (absorption, distribution, metabolism, excretion, and toxicity)…

Modern deep learning tools are remarkably effective in addressing intricate problems. However, their operation as black-box models introduces increased uncertainty in predictions. Additionally, they contend with various challenges,…

One of the unsolved challenges in the field of biometrics and face recognition is Kinship Verification. This problem aims to understand if two people are family-related and how (sisters, brothers, etc.) Solving this problem can give rise to…

Radio-frequency fingerprints~(RFFs) are promising solutions for realizing low-cost physical layer authentication. Machine learning-based methods have been proposed for RFF extraction and discrimination. However, most existing methods are…

For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential malware sample, suspicious email) is deemed…

Deep-learning-based device fingerprinting has recently been recognized as a key enabler for automated network access authentication. Its robustness to impersonation attacks due to the inherent difficulty of replicating physical features is…

Detecting abnormal patterns that deviate from a certain regular repeating pattern in time series is essential in many big data applications. However, the lack of labels, the dynamic nature of time series data, and unforeseeable abnormal…

Deepfake detectors are typically trained on large sets of pristine and generated images, resulting in limited generalization capacity; they excel at identifying deepfakes created through methods encountered during training but struggle with…

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…

Deep neural networks have revolutionized medical image analysis and disease diagnosis. Despite their impressive performance, it is difficult to generate well-calibrated probabilistic outputs for such networks, which makes them…