Related papers: A Study of Using Cepstrogram for Countermeasure Ag…

Replay attacks belong to the class of severe threats against voice-controlled systems, exploiting the easy accessibility of speech signals by recorded and replayed speech to grant unauthorized access to sensitive data. In this work, we…

Though having achieved some progresses, the hand-crafted texture features, e.g., LBP [23], LBP-TOP [11] are still unable to capture the most discriminative cues between genuine and fake faces. In this paper, instead of designing feature by…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Typical fingerprint recognition systems are comprised of a spoof detection module and a subsequent recognition module, running one after the other. In this paper, we reformulate the workings of a typical fingerprint recognition system. In…

Deep learning-based recommendation models (DLRMs) are widely deployed in commercial applications to enhance user experience. However, the large and sparse embedding layers in these models impose substantial memory bandwidth bottlenecks due…

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Training a spoofing countermeasure (CM) that generalizes to various unseen data is desired but challenging. While methods such as data augmentation and self-supervised learning are applicable, the imperfect CM performance on diverse test…

Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

The behavioural theory of concurrent systems states that any concurrent system can be captured by a behaviourally equivalent concurrent Abstract State Machine (cASM). While the theory in general assumes shared locations, it remains valid,…

CNN-based steganalysis has recently achieved very good performance in detecting content-adaptive steganography. At the same time, recent works have shown that, by adopting an approach similar to that used to build adversarial examples, a…

With heightened awareness of data privacy protection, Federated Learning (FL) has attracted widespread attention as a privacy-preserving distributed machine learning method. However, the distributed nature of federated learning also…

Face morphing attacks aim at creating face images that are verifiable to be the face of multiple identities, which can lead to building faulty identity links in operations like border checks. While creating a morphed face detector (MFD),…

In this paper, we propose an effective and robust method of spatial feature extraction for acoustic scene analysis utilizing partially synchronized and/or closely located distributed microphones. In the proposed method, a new cepstrum…

Conformance checking, one of the main process mining operations, aims to identify discrepancies between a process model and an event log. The model represents the expected behaviour, whereas the event log represents the actual process…

Biological systems leverage top-down feedback for visual processing, yet most artificial vision models succeed in image classification using purely feedforward or recurrent architectures, calling into question the functional significance of…

We utilize the dynamics involved in the imaging of a fingerprint on a touch-based fingerprint reader, such as perspiration, changes in skin color (blanching), and skin distortion, to differentiate real fingers from spoof (fake) fingers.…

Machine learning inference engine is of great interest to smart edge computing. Compute-in-memory (CIM) architecture has shown significant improvements in throughput and energy efficiency for hardware acceleration. Emerging non-volatile…

In recent years, many backdoor attacks based on training data poisoning have been proposed. However, in practice, those backdoor attacks are vulnerable to image compressions. When backdoor instances are compressed, the feature of specific…

A speech spoofing countermeasure (CM) that discriminates between unseen spoofed and bona fide data requires diverse training data. While many datasets use spoofed data generated by speech synthesis systems, it was recently found that data…