相关论文: Subject-level Inference for Realistic Text Anonymi…

In speaker anonymization, speech recordings are modified in a way that the identity of the speaker remains hidden. While this technology could help to protect the privacy of individuals around the globe, current research restricts this by…

As social media becomes a hotbed for the spread of misinformation, the crucial task of rumor detection has witnessed promising advances fostered by open-source benchmark datasets. Despite being widely used, we find that these datasets…

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we…

Model memorization has implications for both the generalization capacity of machine learning models and the privacy of their training data. This paper investigates label memorization in binary classification models through two novel passive…

In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…

Large Language Models (LLMs) often inherit biases from the web data they are trained on, which contains stereotypes and prejudices. Current methods for evaluating and mitigating these biases rely on bias-benchmark datasets. These benchmarks…

Removing Personally Identifiable Information (PII) from clinical notes in Electronic Health Records (EHRs) is essential for research and AI development. While Large Language Models (LLMs) are powerful, their high computational costs and the…

Membership inference attacks allow a malicious entity to predict whether a sample is used during training of a victim model or not. State-of-the-art membership inference attacks have shown to achieve good accuracy which poses a great…

In an age of voice-enabled technology, voice anonymization offers a solution to protect people's privacy, provided these systems work equally well across subgroups. This study investigates bias in voice anonymization systems within the…

Membership Inference Attacks (MIAs) have emerged as a valuable framework for evaluating privacy leakage by machine learning models. Score-based MIAs are distinguished, in particular, by their ability to exploit the confidence scores that…

In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts are much larger than…

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on…

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting…

Sharing sensitive texts for scientific purposes requires appropriate techniques to protect the privacy of patients and healthcare personnel. Anonymizing textual data is particularly challenging due to the presence of diverse unstructured…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

Voice anonymization techniques have been found to successfully obscure a speaker's acoustic identity in short, isolated utterances in benchmarks such as the VoicePrivacy Challenge. In practice, however, utterances seldom occur in isolation:…

In this paper, we propose a variational approach to weakly supervised document-level multi-aspect sentiment classification. Instead of using user-generated ratings or annotations provided by domain experts, we use target-opinion word pairs…

Prediction-powered inference (PPI) is a method that improves statistical estimates based on limited human-labeled data. PPI achieves this by combining small amounts of human-labeled data with larger amounts of data labeled by a reasonably…

Speaker, author, and other biometric identification applications often compare a sample's similarity to a database of templates to determine the identity. Given that data may be noisy and similarity measures can be inaccurate, such a…

Text attribute person search aims to find specific pedestrians through given textual attributes, which is very meaningful in the scene of searching for designated pedestrians through witness descriptions. The key challenge is the…