相关论文: Robust Privacy: Inference-Time Privacy through Cer…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

The remarkable proliferation of deep learning across various industries has underscored the importance of data privacy and security in AI pipelines. As the evolution of sophisticated Membership Inference Attacks (MIAs) threatens the secrecy…

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

This short note highlights some links between two lines of research within the emerging topic of trustworthy machine learning: differential privacy and robustness to adversarial examples. By abstracting the definitions of both notions, we…

Reinforcement Learning (RL) enables agents to learn how to perform various tasks from scratch. In domains like autonomous driving, recommendation systems, and more, optimal RL policies learned could cause a privacy breach if the policies…

Increasing use of machine learning (ML) technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing…

Test-time defenses are used to improve the robustness of deep neural networks to adversarial examples during inference. However, existing methods either require an additional trained classifier to detect and correct the adversarial samples,…

We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant…

Private machine learning involves addition of noise while training, resulting in lower accuracy. Intuitively, greater stability can imply greater privacy and improve this privacy-utility tradeoff. We study this role of stability in private…

As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely…

Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects the privacy of client data. So far these two emerging areas…

The growing concern about data privacy has led to the development of private inference (PI) frameworks in client-server applications which protects both data privacy and model IP. However, the cryptographic primitives required yield…

Privacy protection methods, such as differentially private mechanisms, introduce noise into resulting statistics which often produces complex and intractable sampling distributions. In this paper, we propose a simulation-based "repro…

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…

Reinforcement learning (RL) is a powerful tool for sequential decision-making, but its application is often hindered by privacy concerns arising from its interaction data. This challenge is particularly acute in advanced networked systems,…

Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…

Differential Privacy (DP) is the de facto standard for reasoning about the privacy guarantees of a training algorithm. Despite the empirical observation that DP reduces the vulnerability of models to existing membership inference (MI)…

Adversarial robustness, the ability of a model to withstand manipulated inputs that cause errors, is essential for ensuring the trustworthiness of machine learning models in real-world applications. However, previous studies have shown that…

Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under-estimated by finite-sampling approximations of…

We give the first polynomial time and sample $(\epsilon, \delta)$-differentially private (DP) algorithm to estimate the mean, covariance and higher moments in the presence of a constant fraction of adversarial outliers. Our algorithm…