Related papers: EmoAttack: Utilizing Emotional Voice Conversion fo…
Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…
In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Such systems, while achieving the state-of-the-art performance on clean data, perform abnormally on inputs with…
Despite their immense popularity, deep learning-based acoustic systems are inherently vulnerable to adversarial attacks, wherein maliciously crafted audios trigger target systems to misbehave. In this paper, we present SirenAttack, a new…
Emotional voice conversion (EVC) is one way to generate expressive synthetic speech. Previous approaches mainly focused on modeling one-to-one mapping, i.e., conversion from one emotional state to another emotional state, with Mel-cepstral…
Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…
Emotional voice conversion (EVC) seeks to convert the emotional state of an utterance while preserving the linguistic content and speaker identity. In EVC, emotions are usually treated as discrete categories overlooking the fact that speech…
Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated,…
There are growing implications surrounding generative AI in the speech domain that enable voice cloning and real-time voice conversion from one individual to another. This technology poses a significant ethical threat and could lead to…
Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction. The robustness of SER models is crucial, particularly in…
Voice anonymization systems aim to protect speaker privacy by obscuring vocal traits while preserving the linguistic content relevant for downstream applications. However, because these linguistic cues remain intact, they can be exploited…
Deep neural networks (DNNs) have achieved remarkable success in the field of natural language processing (NLP), leading to widely recognized applications such as ChatGPT. However, the vulnerability of these models to adversarial attacks…
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…
Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…
Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion…
This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers. By doing so, we make the backdoor attack challenging to detect for legitimate users, and thus, potentially more dangerous. We…
This paper highlights vulnerabilities of deep learning-driven semantic communications to backdoor (Trojan) attacks. Semantic communications aims to convey a desired meaning while transferring information from a transmitter to its receiver.…
Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable to backdoor attacks, where some specific trigger patterns…
Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…
Audio deepfake is so sophisticated that the lack of effective detection methods is fatal. While most detection systems primarily rely on low-level acoustic features or pretrained speech representations, they frequently neglect high-level…
Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…