Fully Decentralized Certified Unlearning

The introduction of DAASH, a meta-attack framework, marks a significant advancement in generating effective and perceptually aligned adversarial examples, addressing the limitations of traditional Lp-norm constrained methods. This framework strategically composes existing attack methods in a multi-stage process, enhancing the perceptual alignment of adversarial examples.

Recent research challenges the notion that weight oscillations during Quantization Aware Training (QAT) are merely undesirable effects, proposing instead that they are crucial for enhancing the robustness of neural networks. The study demonstrates that these oscillations, induced by a new regularizer, can help maintain performance across various quantization levels, particularly in models like ResNet-18 and Tiny Vision Transformer evaluated on CIFAR-10 and Tiny ImageNet datasets.

A recent study explores the potential of pruning at initialization (PaI) by drawing inspiration from iterative pruning methods, aiming to enhance performance in deep learning models. The research highlights the significance of identifying surviving subnetworks based on initial features, which could lead to more efficient pruning strategies and reduced training costs, especially as neural networks grow in size.

A novel Conditional Neural Cellular Automata (c-NCA) architecture has been proposed, enabling the generation of distinct topological structures, specifically MNIST digits, from a single seed. This approach emphasizes local interactions and translation equivariance, diverging from traditional generative models that rely on global reception fields.

A recent study has focused on the influential factors extracted by variational autoencoders (VAEs), highlighting the challenge of supervising learned representations without manual intervention. The research emphasizes the role of mutual information between inputs and learned factors as a key indicator for identifying influential factors, revealing that some factors may be non-influential and can be disregarded in data reconstruction.

A new reduced-space formulation for optimizing trained neural networks has been proposed, which evaluates the network's outputs and derivatives on a GPU. This method treats the neural network as a 'gray box,' leading to faster solves and fewer iterations compared to traditional full-space formulations. The approach has been demonstrated on two optimization problems, including adversarial generation for a classifier trained on MNIST images.

A recent study highlights the vulnerabilities of backdoor defenses in neural networks when subjected to post-training quantization, revealing that INT8 quantization leads to a 0% detection rate for all evaluated defenses while attack success rates remain above 99%. This raises concerns about the effectiveness of existing security measures in machine learning systems.

A recent study has introduced a pruned version of Capsule Networks (CapsNets), demonstrating that it can operate up to 9.90 times faster than traditional architectures by eliminating 95% of Primary Capsules while maintaining accuracy across various datasets, including MNIST and CIFAR-10.