相关论文: Voice Privacy Preservation with Multiple Random Or…

Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Gradient leakage attacks are considered one of the wickedest privacy threats in deep learning as attackers covertly spy gradient updates during iterative training without compromising model training quality, and yet secretly reconstruct…

Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is through the lens of differential privacy. In this framework,…

In this paper, we present AltVoice -- a system designed to help user's protect their privacy when using remotely accessed voice services. The system allows a user to conceal their true voice identity information with no cooperation from the…

We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or…

The privacy of data is a major challenge in machine learning as a trained model may expose sensitive information of the enclosed dataset. Besides, the limited computation capability and capacity of edge devices have made cloud-hosted…

This paper addresses the privacy and security concerns associated with deep neural language models, which serve as crucial components in various modern AI-based applications. These models are often used after being pre-trained and…

In this paper, we propose a new key-based defense focusing on both efficiency and robustness. Although the previous key-based defense seems effective in defending against adversarial examples, carefully designed adaptive attacks can bypass…

Voice authentication has undergone significant changes from traditional systems that relied on handcrafted acoustic features to deep learning models that can extract robust speaker embeddings. This advancement has expanded its applications…

Passwords remain one of the most common methods for securing sensitive data in the digital age. However, weak password choices continue to pose significant risks to data security and privacy. This study aims to solve the problem by focusing…

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…

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the…

A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy. In this work, we study whether a non-private learning algorithm can be made private by relying on an instance-encoding…

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First, we analyze two types of strategies for privacy-enhanced federated learning: (i) gradient pruning with random…

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our…

Speaker anonymization is an effective privacy protection solution that aims to conceal the speaker's identity while preserving the naturalness and distinctiveness of the original speech. Mainstream approaches use an utterance-level vector…

Nowadays, facial recognition systems are still vulnerable to adversarial attacks. These attacks vary from simple perturbations of the input image to modifying the parameters of the recognition model to impersonate an authorised subject.…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…