Related papers: Batch Normalization Amplifies Memorization and Pri…
As machine learning models increasingly process sensitive data, understanding their vulnerability to privacy attacks is vital. Membership inference attacks (MIAs) exploit model responses to infer whether specific data points were used…
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…
Batch Normalization (BN) has been used extensively in deep learning to achieve faster training process and better resulting models. However, whether BN works strongly depends on how the batches are constructed during training and it may not…
Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved significant performances in the visual recognition task. Despite…
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks. For instance, BN depends on batch…
Spiking Neural Networks (SNNs) are increasingly explored for their energy efficiency and robustness in real-world applications, yet their privacy risks remain largely unexamined. In this work, we investigate the susceptibility of SNNs to…
Quantifying the impact of individual data samples on machine learning models is an open research problem. This is particularly relevant when complex and high-dimensional relationships have to be learned from a limited sample of the data…
Batch normalization (BN) has become a standard technique for training the modern deep networks. However, its effectiveness diminishes when the batch size becomes smaller, since the batch statistics estimation becomes inaccurate. That…
Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…
Adversarial training is one of the main defenses against adversarial attacks. In this paper, we provide the first rigorous study on diagnosing elements of adversarial training, which reveals two intriguing properties. First, we study the…
Bayesian networks (BN) are probabilistic graphical models that enable efficient knowledge representation and inference. These have proven effective across diverse domains, including healthcare, bioinformatics and economics. The structure…
Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of the training loss. Previous works indicate that the noise is…
Batch Normalization (BN) is essential to effectively train state-of-the-art deep Convolutional Neural Networks (CNN). It normalizes inputs to the layers during training using the statistics of each mini-batch. In this work, we study BN from…
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks,…
Batch normalization dramatically increases the largest trainable depth of residual networks, and this benefit has been crucial to the empirical success of deep residual networks on a wide range of benchmarks. We show that this key benefit…
Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…
Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent work has shown that…
Batch normalization (BN) is comprised of a normalization component followed by an affine transformation and has become essential for training deep neural networks. Standard initialization of each BN in a network sets the affine…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…
Regularization is a set of techniques that are used to improve the generalization ability of deep neural networks. In this paper, we introduce spectral batch normalization (SBN), a novel effective method to improve generalization by…