Related papers: Generalization Techniques Empirically Outperform D…

Attacks that aim to identify the training data of public neural networks represent a severe threat to the privacy of individuals participating in the training data set. A possible protection is offered by anonymization of the training data…

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…

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even…

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…

Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to…

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…

Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries. We identify severe pitfalls in existing empirical privacy…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development. Differential privacy (DP) has emerged as one canonical…

Machine learning models are increasingly made available to the masses through public query interfaces. Recent academic work has demonstrated that malicious users who can query such models are able to infer sensitive information about…

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving…

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)…

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive…

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

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…

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique…

Nowadays, owners and developers of deep learning models must consider stringent privacy-preservation rules of their training data, usually crowd-sourced and retaining sensitive information. The most widely adopted method to enforce privacy…

Data holders are increasingly seeking to protect their user's privacy, whilst still maximizing their ability to produce machine models with high quality predictions. In this work, we empirically evaluate various implementations of…