相关论文: Mitigating Gradient Inversion Risks in Language Mo…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Backdoor attacks have posed a significant threat to the security of deep neural networks (DNNs). Despite considerable strides in developing defenses against backdoor attacks in the visual domain, the specialized defenses for the audio…

The intellectual property of deep image-to-image models can be protected by the so-called box-free watermarking. It uses an encoder and a decoder, respectively, to embed into and extract from the model's output images invisible copyright…

In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties of IRs can leak training-set membership signals, enabling Membership Inference Attacks (MIAs)…

As edge devices gain stronger computing power, deploying high-performance DNN models on untrusted hardware has become a practical approach to cut inference latency and protect user data privacy. Given high model training costs and user…

Graph neural networks (GNNs) have exhibited superior performance in various classification tasks on graph-structured data. However, they encounter the potential vulnerability from the link stealing attacks, which can infer the presence of a…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstructing clients' private data from the leaked gradients.…

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…

Disclosing information via the publication of a machine learning model poses significant privacy risks. However, auditing this disclosure across every datapoint during the training of Large Language Models (LLMs) is computationally…

The widespread deployment of deep learning models in privacy-sensitive domains has amplified concerns regarding privacy risks, particularly those stemming from gradient leakage during training. Current privacy assessments primarily rely on…

Inferring the latent variable generating a given test sample is a challenging problem in Generative Adversarial Networks (GANs). In this paper, we propose InvGAN - a novel framework for solving the inference problem in GANs, which involves…

Federated Learning (FL) has become a cornerstone of privacy protection, shifting the paradigm towards localizing sensitive data while only sending model gradients to a central server. This strategy is designed to reinforce privacy…

Diffusion models are becoming defector generative models, which generate exceptionally high-resolution image data. Training effective diffusion models require massive real data, which is privately owned by distributed parties. Each data…

Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…

Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model by transmitting locally computed gradients to a central…

Advances in Federated Learning and an abundance of user data have enabled rich collaborative learning between multiple clients, without sharing user data. This is done via a central server that aggregates learning in the form of weight…

Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced…

With the rapid development of deep learning, existing generative text steganography methods based on autoregressive models have achieved success. However, these autoregressive steganography approaches have certain limitations. Firstly,…

Semantic communication systems, which leverage Generative AI (GAI) to transmit semantic meaning rather than raw data, are poised to revolutionize modern communications. However, they are vulnerable to backdoor attacks, a type of poisoning…