相关论文: Going In Style: Audio Backdoors Through Stylistic …

Despite significant advancements in computer vision, semantic segmentation models may be susceptible to backdoor attacks. These attacks, involving hidden triggers, aim to cause the models to misclassify instances of the victim class as the…

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…

While most music generation models use textual or parametric conditioning (e.g. tempo, harmony, musical genre), we propose to condition a language model based music generation system with audio input. Our exploration involves two distinct…

Backdoor attacks pose a significant threat when using third-party data for deep learning development. In these attacks, data can be manipulated to cause a trained model to behave improperly when a specific trigger pattern is applied,…

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 manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

We investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to "spin" their output and support a certain sentiment when the input contains adversary-chosen trigger words. For example,…

With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious threat: an adversary who poisons a small fraction of training data can implant a hidden…

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored,…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it…

Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is…

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…

Outsourced training and machine learning as a service have resulted in novel attack vectors like backdoor attacks. Such attacks embed a secret functionality in a neural network activated when the trigger is added to its input. In most works…

The rise of multimodal large language models has introduced innovative human-machine interaction paradigms but also significant challenges in machine learning safety. Audio-Language Models (ALMs) are especially relevant due to the intuitive…

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,…

Style transfer is a technique for combining two images based on the activations and feature statistics in a deep learning neural network architecture. This paper studies the analogous task in the audio domain and takes a critical look at…

Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitatively model vulnerability patterns. This work pioneers the…

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…