相关论文: Preserving Cross-Modal Stability for Visual Unlear…

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem…

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

The core challenge of machine unlearning is to strike a balance between target knowledge removal and non-target knowledge retention. In the context of Multimodal Large Language Models (MLLMs), this challenge becomes even more pronounced, as…

Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the…

Human action recognition (HAR) with multi-modal inputs (RGB-D, skeleton, point cloud) can achieve high accuracy but typically relies on large labeled datasets and degrades sharply when sensors fail or are noisy. We present Robust…

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the…

Machine unlearning, the ability to erase the effect of specific training samples without retraining from scratch, is critical for privacy, regulation, and efficiency. However, most progress in unlearning has been empirical, with little…

Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process. While progress has been made in unimodal domains like text and image…

Machine unlearning allows data owners to erase the impact of their specified data from trained models. Unfortunately, recent studies have shown that adversaries can recover the erased data, posing serious threats to user privacy. An…

Various state-of-the-art self-supervised visual representation learning approaches take advantage of data from multiple sensors by aligning the feature representations across views and/or modalities. In this work, we investigate how…

Multimodal affective computing aims to predict humans' sentiment, emotion, intention, and opinion using language, acoustic, and visual modalities. However, current models often learn spurious correlations that harm generalization under…

Deep learning models frequently encounter feature uncertainty in diverse learning scenarios, significantly impacting their performance and reliability. This challenge is particularly complex in multi-modal scenarios, where models must…

Although Multimodal Large Language Models (MLLMs) have achieved remarkable progress across many domains, their training on large-scale multimodal datasets raises serious privacy concerns, making effective machine unlearning increasingly…

While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can…

Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copyright, and safety concerns. However, recent studies reveal a critical vulnerability:…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Machine Unlearning (MU) aims to remove the information of specific training data from a trained model, ensuring compliance with privacy regulations and user requests. While one line of existing MU methods relies on linear parameter updates…

As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data.…

LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multimodal LLMs as they integrate information from multiple…

Cross-lingual Cross-modal Retrieval (CCR) is an essential task in web search, which aims to break the barriers between modality and language simultaneously and achieves image-text retrieval in the multi-lingual scenario with a single model.…