Related papers: IncogniText: Privacy-enhancing Conditional Text An…

The widespread exchange of digital documents in various domains has resulted in abundant private information being shared. This proliferation necessitates redaction techniques to protect sensitive content and user privacy. While numerous…

Speaker anonymization is the task of modifying a speech recording such that the original speaker cannot be identified anymore. Since the first Voice Privacy Challenge in 2020, along with the release of a framework, the popularity of this…

Privacy and security are major concerns when communicating speech signals to cloud services such as automatic speech recognition (ASR) and speech emotion recognition (SER). Existing solutions for speech anonymization mainly focus on voice…

Today, the publication of microdata poses a privacy threat. Vast research has striven to define the privacy condition that microdata should satisfy before it is released, and devise algorithms to anonymize the data so as to achieve this…

Benchmarking is the de-facto standard for evaluating LLMs, due to its speed, replicability and low cost. However, recent work has pointed out that the majority of the open source benchmarks available today have been contaminated or leaked…

We propose DarkStream, a streaming speech synthesis model for real-time speaker anonymization. To improve content encoding under strict latency constraints, DarkStream combines a causal waveform encoder, a short lookahead buffer, and…

Current online translation services require sending user text to cloud servers, posing a risk of privacy leakage when the text contains sensitive information. This risk hinders the application of online translation services in…

In-context learning (ICL) is an important capability of Large Language Models (LLMs), enabling these models to dynamically adapt based on specific, in-context exemplars, thereby improving accuracy and relevance. However, LLM's responses may…

The increasing use of machine learning (ML) for Just-In-Time (JIT) defect prediction raises concerns about privacy leakage from software analytics data. Existing anonymization methods, such as tabular transformations and graph…

Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversarial image…

The rapid development of large language models (LLMs) has yielded impressive success in various downstream tasks. However, the vast potential and remarkable capabilities of LLMs also raise new security and privacy concerns if they are…

In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive…

The field of privacy-preserving Natural Language Processing has risen in popularity, particularly at a time when concerns about privacy grow with the proliferation of Large Language Models. One solution consistently appearing in recent…

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…

The rise of chronic diseases and pandemics like COVID-19 has emphasized the need for effective patient data processing while ensuring privacy through anonymization and de-identification of protected health information (PHI). Anonymized data…

The increasing prevalence of computer vision applications necessitates handling vast amounts of visual data, often containing personal information. While this technology offers significant benefits, it should not compromise privacy. Data…

Privacy enhancing technologies, or PETs, have been hailed as a promising means to protect privacy without compromising on the functionality of digital services. At the same time, and partly because they may encode a narrow conceptualization…

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

Whistleblowing is essential for ensuring transparency and accountability in both public and private sectors. However, (potential) whistleblowers often fear or face retaliation, even when reporting anonymously. The specific content of their…