Related papers: RecPS: Privacy Risk Scoring for Recommender System…

Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differentially private pipeline…

In this work, we systematically explore the data privacy issues of dataset pruning in machine learning systems. Our findings reveal, for the first time, that even if data in the redundant set is solely used before model training, its…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…

Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health…

Analyzing time-series data that contains personal information, particularly in the medical field, presents serious privacy concerns. Sensitive health data from patients is often used to train machine learning models for diagnostics and…

Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, there is still a gap between the existing defense approaches…

We present a new Python toolkit called RecWizard for Conversational Recommender Systems (CRS). RecWizard offers support for development of models and interactive user interface, drawing from the best practices of the Huggingface ecosystems.…

Membership Inference Attacks (MIA) enable to empirically assess the privacy of a machine learning algorithm. In this paper, we propose TAMIS, a novel MIA against differentially-private synthetic data generation methods that rely on…

Preserving the privacy of preferences (or rewards) of a sequential decision-making agent when decisions are observable is crucial in many physical and cybersecurity domains. For instance, in wildlife monitoring, agents must allocate…

Membership inference attacks (MIAs) pose a critical privacy threat to fine-tuned large language models (LLMs), especially when models are adapted to domain-specific tasks using sensitive data. While prior black-box MIA techniques rely on…

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While…

With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized data to train…

Recommender systems (RecSys) have been well developed to assist user decision making. Traditional RecSys usually optimize a single objective (e.g., rating prediction errors or ranking quality) in the model. There is an emerging demand in…

Many users make quick decisions that affect their data privacy without due consideration of their values. One such decision is whether to download a smartphone app to their device. Previous work has suggested a relationship between values,…

AI creates and exacerbates privacy risks, yet practitioners lack effective resources to identify and mitigate these risks. We present Privy, a tool that guides practitioners without privacy expertise through structured privacy impact…

People candidly discuss sensitive topics online under the perceived safety of anonymity; yet, for many, this perceived safety is tenuous, as miscalibrated risk perceptions can lead to over-disclosure. Recent advances in Natural Language…

The convergence of artificial AI and XR technologies (AI XR) promises innovative applications across many domains. However, the sensitive nature of data (e.g., eye-tracking) used in these systems raises significant privacy concerns, as…

Analyzing privacy threats in software products is an essential part of software development to ensure systems are privacy-respecting; yet it is still a far from trivial activity. While there have been many advancements in the past decade,…

As the final stage of the multi-stage recommender system (MRS), reranking directly affects users' experience and satisfaction, thus playing a critical role in MRS. Despite the improvement achieved in the existing work, three issues are yet…

Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is important to align LLMs to generate texts according to acceptable…