Related papers: Practical Acoustic Eavesdropping On Typed Passphra…
This work presents a novel approach for speaker diarization to leverage lexical information provided by automatic speech recognition. We propose a speaker diarization system that can incorporate word-level speaker turn probabilities with…
Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: voice cloning, spoofing, etc. Anonymization aims to make the…
Network slicing in 5G and the future 6G networks will enable the creation of multiple virtualized networks on a shared physical infrastructure. This innovative approach enables the provision of tailored networks to accommodate specific…
Detecting weaknesses in cryptographic algorithms is of utmost importance for designing secure information systems. The state-of-the-art soft analytical side-channel attack (SASCA) uses physical leakage information to make probabilistic…
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…
This paper highlights security issues that can arise when incorrect assumptions are made on the capabilities of an eavesdropper. In particular, we analyze a channel model based on a split Binary Symmetric Channel (BSC). Corresponding…
Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…
Recently, opportunities to transmit speech data to deep learning models executed in the cloud have increased. This has led to growing concerns about speech privacy, including both speaker-specific information and the linguistic content of…
The arm race between hardware security engineers and side-channel researchers has become more competitive with more sophisticated attacks and defenses in the last decade. While modern hardware features improve the system performance…
The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that…
In the past, two main approaches for the purpose of authentication, including information-theoretic authentication codes and complexity-theoretic message authentication codes (MACs), were almost independently developed. In this paper, we…
This dissertation proposes a framework of user-centered security in Natural Language Processing (NLP), and demonstrates how it can improve the accessibility of related research. Accordingly, it focuses on two security domains within NLP…
Passwords remain the primary authentication method, yet user-created passwords are often the weakest due to the security-usability trade-off. Although AI-based password generators are emerging, little is known about their effectiveness and…
Cloud computing offers users scalable platforms and low resource cost. At the same time, the off-site location of the resources of this service model makes it more vulnerable to certain types of adversarial actions. Cloud computing has not…
Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech…
When domain experts are needed to perform data annotation for complex machine-learning tasks, reducing annotation effort is crucial in order to cut down time and expenses. For cases when there are no annotations available, one approach is…
CAPTCHAs are designed to prevent malicious bot programs from abusing websites. Most online service providers deploy audio CAPTCHAs as an alternative to text and image CAPTCHAs for visually impaired users. However, prior research…
Reusing passwords across multiple websites is a common practice that compromises security. Recently, Blum and Vempala have proposed password strategies to help people calculate, in their heads, passwords for different sites without…
It is common practice to outsource the training of machine learning models to cloud providers. Clients who do so gain from the cloud's economies of scale, but implicitly assume trust: the server should not deviate from the client's training…
The rapid advancements in AI voice cloning, fueled by machine learning, have significantly impacted text-to-speech (TTS) and voice conversion (VC) fields. While these developments have led to notable progress, they have also raised concerns…