相关论文: MU-Bench: A Multitask Multimodal Benchmark for Mac…

Existing machine unlearning (MU) approaches exhibit significant sensitivity to hyperparameters, requiring meticulous tuning that limits practical deployment. In this work, we first empirically demonstrate the instability and suboptimal…

Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weight perturbation-based…

As text-to-image diffusion models gain widespread commercial applications, there are increasing concerns about unethical or harmful use, including the unauthorized generation of copyrighted or sensitive content. Concept unlearning has…

Multi-label learning deals with the classification problems where each instance can be assigned with multiple labels simultaneously. Conventional multi-label learning approaches mainly focus on exploiting label correlations. It is usually…

Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations,…

Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been analyzed in centralized and server-orchestrated federated…

Multimodal physiological data powers clinical AI systems from intensive care units to wearable devices, but sensors routinely fail in practice. Two failure modes are common: modality missing, where an entire channel is absent, and…

Machine unlearning has emerged as an important component in developing safe and trustworthy models. Prior work on fact unlearning in LLMs has mostly focused on removing a specified target fact robustly, but often overlooks its deductive…

Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes. We remove the requirement…

Visual modality is the most vulnerable to privacy leakage in real-world multimodal applications like autonomous driving with visual and radar data; Machine unlearning removes specific training data from pre-trained models to address privacy…

Approximate machine unlearning (AMU) enables models to `forget' specific training data through specialized fine-tuning on a retained (and forget) subset of training set. However, processing this large retained subset still dominates…

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

With the rapid advancement of AI applications, the growing needs for data privacy and model robustness have highlighted the importance of machine unlearning, especially in thriving graph-based scenarios. However, most existing graph…

Large Language Model (LLM) unlearning has recently gained significant attention, driven by the need to remove unwanted information, such as private, sensitive, or copyrighted content, from LLMs. However, conventional unlearning approaches…

Addressing missing modalities and limited labeled data is crucial for advancing robust multimodal learning. We propose Robult, a scalable framework designed to mitigate these challenges by preserving modality-specific information and…

Class imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. One efficient and flexible strategy to deal with this problem is to employ sampling techniques before training a multi-label…

Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models (MLLMs) have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM…

We consider the task of optimally fine-tuning pre-trained multilingual models, given small amounts of unlabelled target data and an annotation budget. In this paper, we introduce DEMUX, a framework that prescribes the exact data-points to…

Machine unlearning aims to remove specific data influences from trained models, a capability essential for adhering to copyright laws and ensuring AI safety. Current unlearning metrics typically measure success by monitoring the model's…

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…