Related papers: Adversarial Correctness and Privacy for Probabilis…
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)…
The focus of this work is \emph{hardness-preserving} transformations of somewhat limited pseudorandom functions families (PRFs) into ones with more versatile characteristics. Consider the problem of \emph{domain extension} of pseudorandom…
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…
Isolated qubits are a special class of quantum devices, which can be used to implement tamper-resistant cryptographic hardware such as one-time memories (OTM's). Unfortunately, these OTM constructions leak some information, and standard…
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…
We consider differentially private algorithms for reinforcement learning in continuous spaces, such that neighboring reward functions are indistinguishable. This protects the reward information from being exploited by methods such as…
Differential privacy (DP) provides rigorous privacy guarantees on individual's data while also allowing for accurate statistics to be conducted on the overall, sensitive dataset. To design a private system, first private algorithms must be…
Local differential privacy (LDP) gives a strong privacy guarantee to be used in a distributed setting like federated learning (FL). LDP mechanisms in FL protect a client's gradient by randomizing it on the client; however, how can we…
This paper presents a privacy-preserving event detection scheme based on measurements made by a network of sensors. A diameter-like decision statistic made up of the marginal types of the measurements observed by the sensors is employed.…
We show how to construct pseudorandom permutations (PRPs) that remain secure even if the adversary can query the permutation, both in the forward and reverse directions, on a quantum superposition of inputs. Such quantum-secure PRPs have…
Privacy is a growing concern in modern deep-learning systems and applications. Differentially private (DP) training prevents the leakage of sensitive information in the collected training data from the trained machine learning models. DP…
Differential privacy is a precise mathematical constraint meant to ensure privacy of individual pieces of information in a database even while queries are being answered about the aggregate. Intuitively, one must come to terms with what…
The neighbourhood-based Collaborative Filtering is a widely used method in recommender systems. However, the risks of revealing customers' privacy during the process of filtering have attracted noticeable public concern recently.…
"f differential privacy" (fDP) is a recent definition for privacy privacy which can offer improved predictions of "privacy loss". It has been used to analyse specific privacy mechanisms, such as the popular Gaussian mechanism. In this paper…
We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive…
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…
Training machine learning models with differential privacy (DP) limits an adversary's ability to infer sensitive information about the training data. It can be interpreted as a bound on adversary's capability to distinguish two adjacent…
To analyze the privacy guarantee of personal data in a database that is subject to queries it is necessary to model the prior knowledge of a possible attacker. Differential privacy considers a worst-case scenario where he knows almost…
Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The…
In addition to their security properties, adversarial machine-learning attacks and defenses have political dimensions. They enable or foreclose certain options for both the subjects of the machine learning systems and for those who deploy…