Related papers: Leakage of Dataset Properties in Multi-Party Machi…
Neural networks pose a privacy risk due to their propensity to memorise and leak training data. We show that unique features occurring only once in training data are memorised by discriminative multi-layer perceptrons and convolutional…
Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns. On one hand, potential gains are highly anticipated if different organizations…
Secure multi-party computation (MPC) facilitates privacy-preserving computation between multiple parties without leaking private information. While most secure deep learning techniques utilize MPC operations to achieve feasible…
The widespread deployment of deep learning models in privacy-sensitive domains has amplified concerns regarding privacy risks, particularly those stemming from gradient leakage during training. Current privacy assessments primarily rely on…
Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive---new systems and models are being deployed in every…
As machine learning algorithms are deployed on sensitive data in critical decision making processes, it is becoming increasingly important that they are also private and fair. In this paper, we show that, when the data has a long-tailed…
The data is an important asset of an organization and it is essential to keep this asset secure. It requires security in whatever state is it i.e. data at rest, data in use, and data in transit. There is a need to pay more attention to it…
Historically, machine learning methods have not been designed with security in mind. In turn, this has given rise to adversarial examples, carefully perturbed input samples aimed to mislead detection at test time, which have been applied to…
Hyperparameters are critical in machine learning, as different hyperparameters often result in models with significantly different performance. Hyperparameters may be deemed confidential because of their commercial value and the…
We consider the problems of secret sharing and multiparty computation, assuming that agents prefer to get the secret (resp., function value) to not getting it, and secondarily, prefer that as few as possible of the other agents get it. We…
We present a framework for experimenting with secure multi-party computation directly in TensorFlow. By doing so we benefit from several properties valuable to both researchers and practitioners, including tight integration with ordinary…
Recent work~\cite{Liu2016} has shown that dependencies between items in a dataset can lead to privacy leaks. We extend this concept to privacy-preserving transformations, considering a broader set of dependencies captured by correlation…
We investigate the contents of web-scraped data for training AI systems, at sizes where human dataset curators and compilers no longer manually annotate every sample. Building off of prior privacy concerns in machine learning models, we…
The rise of Artificial Intelligence (AI) has revolutionized numerous industries and transformed the way society operates. Its widespread use has led to the distribution of AI and its underlying data across many intelligent systems. In this…
Centralized systems in the Internet of Things---be it local middleware or cloud-based services---fail to fundamentally address privacy of the collected data. We propose an architecture featuring secure multiparty computation at its core in…
This paper introduces a new attack on recent messaging systems that protect communication metadata. The main observation is that if an adversary manages to compromise a user's friend, it can use this compromised friend to learn information…
The emergence of social and technological networks has enabled rapid sharing of data and information. This has resulted in significant privacy concerns where private information can be either leaked or inferred from public data. The problem…
How to achieve differential privacy in the distributed setting, where the dataset is distributed among the distrustful parties, is an important problem. We consider in what condition can a protocol inherit the differential privacy property…
Code secrets are sensitive assets for software developers, and their leakage poses significant cybersecurity risks. While the rapid development of AI code assistants powered by Code Large Language Models (CLLMs), CLLMs are shown to…
In an ideal world, deployed machine learning models will enhance our society. We hope that those models will provide unbiased and ethical decisions that will benefit everyone. However, this is not always the case; issues arise during the…