Related papers: Machine Unlearning and Continual Learning in Hybri…

Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by…

Analog In-Memory Computing (AIMC) offers a promising solution to the von Neumann bottleneck. However, deploying transformer models on AIMC remains challenging due to their inherent need for flexibility and adaptability across diverse tasks.…

In neuromorphic photonic systems, device operations are typically governed by analog signals, necessitating digital-to-analog converters (DAC) and analog-to-digital converters (ADC). However, data movement between memory and these…

Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully remove sensitive or harmful knowledge, this ``forgotten" information remains precariously…

In computer vision, machine unlearning aims to remove the influence of specific visual concepts or training images without retraining from scratch. Studies show that existing approaches often modify the classifier while leaving internal…

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive…

Neuromorphic computing with non-volatile memory (NVM) can significantly improve performance and lower energy consumption of machine learning tasks implemented using spike-based computations and bio-inspired learning algorithms. High…

The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory like dynamic random-access memory, which reduces energy efficiency and increases training time.…

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

Catastrophic forgetting is a longstanding challenge in continual learning, where models lose knowledge from earlier tasks when learning new ones. While various mitigation strategies have been proposed for Multi-Layer Perceptrons (MLPs),…

Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive multi-sensory data analysis directly on edge intelligent…

Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its true effectiveness against privacy attacks remains unclear.…

Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning has emerged as a…

As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques. Many existing unlearning methods aim to suppress…

Machine Unlearning (MU) technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology, its vulnerabilities are still underexplored, posing…

This article presents a new machine unlearning approach that utilizes multiple Generative Adversarial Network (GAN) based models. The proposed method comprises two phases: i) data reorganization in which synthetic data using the GAN model…

Training machine learning models in an incremental fashion is not only important but also an efficient way to achieve artificial general intelligence. The ability that humans possess of continuous or lifelong learning helps them to not…

The ability to selectively remove knowledge from medical segmentation networks is increasingly important for privacy compliance, ethical deployment, and continual dataset revision. We introduce Erase to Retain, a controllable unlearning…

Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primarily on data-centric or weight-based strategies frequently…

Machine learning based malware detection techniques rely on grayscale images of malware and tends to classify malware based on the distribution of textures in graycale images. Albeit the advancement and promising results shown by machine…