Related papers: From Weak Cues to Real Identities: Evaluating Infe…

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Personalization of LLMs by sociodemographic subgroup often improves user experience, but can also introduce or amplify biases and unfair outcomes across groups. Prior work has employed so-called personas, sociodemographic user attributes…

The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a…

Enormous amounts of data collected from social networks or other online platforms are being published for the sake of statistics, marketing, and research, among other objectives. The consequent privacy and data security concerns have…

Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new risks for sensitive information leakage. We introduce…

We revisit the privacy-utility tradeoff of x-vector speaker anonymization. Existing approaches quantify privacy through training complex speaker verification or identification models that are later used as attacks. Instead, we propose a…

Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts,…

Prior work on LLM-based privacy focuses on norm judgment over synthetic vignettes, rather than how people think about a specific data practice and formulate their opinions. We address this gap by designing PrivacyReasoner, an agent…

Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in…

Operators of online social networks are increasingly sharing potentially sensitive information about users and their relationships with advertisers, application developers, and data-mining researchers. Privacy is typically protected by…

Pseudonymisation provides the means to reduce the privacy impact of monitoring, auditing, intrusion detection, and data collection in general on individual subjects. Its application on data records, especially in an environment with…

Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a…

Despite the growing integration of retrieval-enabled AI agents into society, their safety and ethical behavior remain inadequately understood. In particular, the integration of LLMs and AI agents with external information sources and…

Large Language Models (LLMs) such as ChatGPT can infer personal attributes from seemingly innocuous text, raising privacy risks beyond memorized data leakage. While prior work has demonstrated these risks, little is known about how users…

Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant…

Large Language Models (LLMs) demonstrate impressive capabilities in natural language understanding and generation, but incur high communication overhead and privacy risks in cloud deployments, while facing compute and memory constraints…

State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant privacy concerns. In response, we introduce ConfusionPrompt, a…

Language models (LMs) rely on their parametric knowledge augmented with relevant contextual knowledge for certain tasks, such as question answering. However, the contextual knowledge can contain private information that may be leaked when…

Privacy-preserving machine learning (ML) seeks to balance data utility and privacy, especially as regulations like the GDPR mandate the anonymization of personal data for ML applications. Conventional anonymization approaches often reduce…

Recent advances in ID-free recommender systems have attracted significant attention for effectively addressing the cold start problem. However, their vulnerability to malicious attacks remains largely unexplored. In this paper, we unveil a…