Related papers: Adversarially Robust Bloom Filters: Privacy, Reduc…

As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges.…

Set reconciliation protocols typically make two critical assumptions: they are designed for fixed-sized elements and they are optimized for when the difference cardinality, d, is very small. When adapting to variable-sized elements, the…

Passwords should be easy to remember, yet expiration policies mandate their frequent change. Caught in the crossfire between these conflicting requirements, users often adopt creative methods to perform slight variations over time. While…

Distributed Denial-of-Service (DDoS) is a menace for service provider and prominent issue in network security. Defeating or defending the DDoS is a prime challenge. DDoS make a service unavailable for a certain time. This phenomenon harms…

We extend the idea of word pieces in natural language models to machine learning tasks on opaque ids. This is achieved by applying hash functions to map each id to multiple hash tokens in a much smaller space, similarly to a Bloom filter.…

Bloom Filters are a fundamental and pervasive data structure. Within the growing area of Learned Data Structures, several Learned versions of Bloom Filters have been considered, yielding advantages over classic Filters. Each of them uses a…

We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private estimators with optimal…

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…

Bloom Filters are a space-efficient data structure used for the testing of membership in a set that errs only in the False Positive direction. However, the standard analysis that measures this False Positive rate provides a form of worst…

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

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…

Recent work has suggested enhancing Bloom filters by using a pre-filter, based on applying machine learning to determine a function that models the data set the Bloom filter is meant to represent. Here we model such learned Bloom filters,,…

In statistical learning and analysis from shared data, which is increasingly widely adopted in platforms such as federated learning and meta-learning, there are two major concerns: privacy and robustness. Each participating individual…

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…

We introduce the Deletable Bloom filter (DlBF) as a new spin on the popular data structure based on compactly encoding the information of where collisions happen when inserting elements. The DlBF design enables false-negative-free deletions…

Big Data is the most popular emerging trends that becomes a blessing for human kinds and it is the necessity of day-to-day life. For example, Facebook. Every person involves with producing data either directly or indirectly. Thus, Big Data…

Privacy-preserving record linkage with Bloom filters has become increasingly popular in medical applications, since Bloom filters allow for probabilistic linkage of sensitive personal data. However, since evidence indicates that Bloom…

Recent studies have demonstrated that learned Bloom filters, which combine machine learning with the classical Bloom filter, can achieve superior memory efficiency. However, existing learned Bloom filters face two critical unresolved…

We present a version of the Bloom filter data structure that supports not only the insertion, deletion, and lookup of key-value pairs, but also allows a complete listing of its contents with high probability, as long the number of key-value…

We suggest a method for holding a dictionary data structure, which maps keys to values, in the spirit of Bloom Filters. The space requirements of the dictionary we suggest are much smaller than those of a hashtable. We allow storing n keys,…