Related papers: Privacy Preserving Reinforcement Learning for Popu…
Multimodal Large Language Models (LLMs) are pivotal in revolutionizing customer support and operations by integrating multiple modalities such as text, images, and audio. Federated Prompt Learning (FPL) is a recently proposed approach that…
It is common practice to use data containing personal information to build predictive models in the framework of empirical risk minimization (ERM). While these models can be highly accurate in prediction, sharing the results from these…
Reinforcement Learning from Human Feedback (RLHF) can reveal implicit objectives such as safety considerations that go beyond task completion. In this work, we focus on the common safety criteria embedded in crowd preference datasets, where…
Several randomization mechanisms for local differential privacy (LDP) (e.g., randomized response) are well-studied to improve the utility. However, recent studies show that LDP is generally vulnerable to malicious data providers in nature.…
Multi-Agent Reinforcement Learning currently focuses on implementations where all data and training can be centralized to one machine. But what if local agents are split across multiple tasks, and need to keep data private between each? We…
In settings like vaccination registries, individuals act after observing others, and the resulting public records can expose private information. We study privacy-preserving sequential learning, where agents add endogenous noise to their…
Federated learning (FL) is a new paradigm that enables many clients to jointly train a machine learning (ML) model under the orchestration of a parameter server while keeping the local data not being exposed to any third party. However, the…
We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated…
Preserving privacy in contemporary NLP models allows us to work with sensitive data, but unfortunately comes at a price. We know that stricter privacy guarantees in differentially-private stochastic gradient descent (DP-SGD) generally…
We approach the task of network congestion control in datacenters using Reinforcement Learning (RL). Successful congestion control algorithms can dramatically improve latency and overall network throughput. Until today, no such…
Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework…
Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…
In times of epidemics, swift reaction is necessary to mitigate epidemic spreading. For this reaction, localized approaches have several advantages, limiting necessary resources and reducing the impact of interventions on a larger scale.…
Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public. Existing approaches protect the privacy of labels by flipping them randomly, and then train a…
While robots have previously utilized rule-based systems or probabilistic models for user interaction, the rapid evolution of large language models (LLMs) presents new opportunities to develop LLM-powered robots for enhanced human-robot…
This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type of attack: an attacker eavesdrops on the hidden representations…
Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective…
Differential privacy is a promising privacy-preserving paradigm for statistical query processing over sensitive data. It works by injecting random noise into each query result, such that it is provably hard for the adversary to infer the…
Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…
Differential privacy is a promising privacy-preserving paradigm for statistical query processing over sensitive data. It works by injecting random noise into each query result, such that it is provably hard for the adversary to infer the…