Related papers: Accurate, Explainable, and Private Models: Providi…

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…

When individuals are subject to adverse outcomes from machine learning models, providing a recourse path to help achieve a positive outcome is desirable. Recent work has shown that counterfactual explanations - which can be used as a means…

Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…

Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are…

Machine learning (ML) models can memorize training datasets. As a result, training ML models over private datasets can lead to the violation of individuals' privacy. Differential privacy (DP) is a rigorous privacy notion to preserve the…

Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the…

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision…

Private regression has received attention from both database and security communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed the functional mechanism (Zhang et al. VLDB 2012) for training linear regression models…

Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning…

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel…

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…

Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…

Nowadays, machine learning models and applications have become increasingly pervasive. With this rapid increase in the development and employment of machine learning models, a concern regarding privacy has risen. Thus, there is a legitimate…

Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects. However the majority of prior work has focused on scenarios where a single party owns all the data. In…

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…