相关论文: MASTERKEY: Practical Backdoor Attack Against Speak…

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…

Acoustic side-channel attacks on keyboards can bypass security measures in many systems that use keyboards as one of the input devices. These attacks aim to reveal users' sensitive information by targeting the sounds made by their keyboards…

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick…

Speaker recognition is a popular topic in biometric authentication and many deep learning approaches have achieved extraordinary performances. However, it has been shown in both image and speech applications that deep neural networks are…

It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some…

Non-Intrusive speech quality assessment (NISQA) has gained significant attention for predicting speech's mean opinion score (MOS) without requiring the reference speech. Researchers have gradually started to apply NISQA to various practical…

How secure automatic speaker verification (ASV) technology is? More concretely, given a specific target speaker, how likely is it to find another person who gets falsely accepted as that target? This question may be addressed empirically by…

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Backdoor learning has become an emerging research area towards building a trustworthy machine learning system. While a lot of works have studied the hidden danger of backdoor attacks in image or text classification, there is a limited…

Voice authentication systems remain susceptible to two major threats: backdoor triggered attacks and targeted data poisoning attacks. This dual vulnerability is critical because conventional solutions typically address each threat type…

Self-Supervised Learning (SSL) is an effective paradigm for learning representations from unlabeled data, such as text, images, and videos. However, researchers have recently found that SSL is vulnerable to backdoor attacks. The attacker…

Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient for adversaries to manipulate up to 90\% of the test outputs…

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or…

The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…

A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical…

Membership inference attacks allow adversaries to determine whether a particular example was contained in the model's training dataset. While previous works have confirmed the feasibility of such attacks in various applications, none has…

Current state-of-the-art automatic speaker verification (ASV) systems are vulnerable to presentation attacks, and several countermeasures (CMs), which distinguish bona fide trials from spoofing ones, have been explored to protect ASV.…

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…