相关论文: Bloodroot: When Watermarking Turns Poisonous For S…

The huge supporting training data on the Internet has been a key factor in the success of deep learning models. However, this abundance of public-available data also raises concerns about the unauthorized exploitation of datasets for…

Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the…

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,…

Protecting the use of audio datasets is a major concern for data owners, particularly with the recent rise of audio deep learning models. While watermarks can be used to protect the data itself, they do not allow to identify a deep learning…

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where the adversaries can…

Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual quality. Although recent advances in neural and digital signal processing-based watermarking methods have…

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…

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, reliance on third-party or internet data is common. Recent studies show CL models are vulnerable…

Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can manipulate the…

In the audio modality, state-of-the-art watermarking methods leverage deep neural networks to allow the embedding of human-imperceptible signatures in generated audio. The ideal is to embed signatures that can be detected with high accuracy…

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…

Speech recognition systems driven by DNNs have revolutionized human-computer interaction through voice interfaces, which significantly facilitate our daily lives. However, the growing popularity of these systems also raises special concerns…

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the…

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…

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets ($e.g.$, ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing…