相关论文: Unlearnable Clusters: Towards Label-agnostic Unlea…

The deployment of language models brings challenges in generating reliable information, especially when these models are fine-tuned using human preferences. To extract encoded knowledge without (potentially) biased human labels,…

Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields. However, a significant challenge arises as these models often "hallucinate", i.e.,…

As machine learning continues to develop, and data misuse scandals become more prevalent, individuals are becoming increasingly concerned about their personal information and are advocating for the right to remove their data. Machine…

As large language models become increasingly capable and widely deployed, verifying the provenance of machine-generated content is critical to ensuring trust, safety, and accountability. Watermarking techniques have emerged as a promising…

Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims at adapting a model trained on a labeled source domain to an unlabeled target domain. State-of-the-art object Re-ID approaches adopt clustering algorithms to generate…

Exemplar-based methods rely on informative data points or prototypes to guide the optimization of learning algorithms. Such data facilitate interpretable model design and prediction. Of particular interest is the utility of exemplars in…

As AI-generated images become widespread, reliable watermarking is essential for content verification, copyright enforcement, and combating disinformation. Existing techniques rely on heuristic approaches and lack formal guarantees of…

Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance of deep neural networks. Sample selection is an effective way…

The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to…

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…

We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…

Emerging applications of sensor networks for detection sometimes suggest that classical problems ought be revisited under new assumptions. This is the case of binary hypothesis testing with independent - but not necessarily identically…

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit…

This paper focuses on unpaired multi-view clustering (UMC), a challenging problem where paired observed samples are unavailable across multiple views. The goal is to perform effective joint clustering using the unpaired observed samples in…

While deep neural networks can achieve state-of-the-art performance in many tasks, these models are more fragile than they appear. They are prone to learning spurious correlations in their training data, leading to surprising failure cases.…

Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…

A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction…

Graph-structured datasets often suffer from class imbalance, which complicates node classification tasks. In this work, we address this issue by first providing an upper bound on population risk for imbalanced transductive node…

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to…

Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with…