Related papers: Random Erasing vs. Model Inversion: A Promising De…
Model inversion attacks pose an open challenge to privacy-sensitive applications that use machine learning (ML) models. For example, face authentication systems use modern ML models to compute embedding vectors from face images of the…
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…
In Member Inference (MI) attacks, the adversary try to determine whether an instance is used to train a machine learning (ML) model. MI attacks are a major privacy concern when using private data to train ML models. Most MI attacks in the…
Adversarial examples, or nearly indistinguishable inputs created by an attacker, significantly reduce machine learning accuracy. Theoretical evidence has shown that the high intrinsic dimensionality of datasets facilitates an adversary's…
In several jurisdictions, the regulatory framework on the release and sharing of personal data is being extended to machine learning (ML). The implicit assumption is that disclosing a trained ML model entails a privacy risk for any personal…
Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a…
The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…
Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper…
Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to embeddings (commonly regarded as privacy-preserving), model…
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…
Person re-identification (re-ID) has attracted much attention recently due to its great importance in video surveillance. In general, distance metrics used to identify two person images are expected to be robust under various appearance…
Model inversion attacks pose a significant privacy risk by attempting to reconstruct private training data from trained models. Most of the existing methods either depend on gradient estimation or require white-box access to model…
The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses and patient…
Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increasing deployment of machine learning models in distributed…
As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models. Existing works evidence strong connection between the distinguishability of the training and testing…
Adversarial Missingness (AM) attacks aim to manipulate model fitting by carefully engineering a missing data problem to achieve a specific malicious objective. AM attacks are significantly different from prior data poisoning attacks in that…
Privacy protection has always been an ongoing topic, especially for AI. Currently, a low-cost scheme called Machine Unlearning forgets the private data remembered in the model. Specifically, given a private dataset and a trained neural…
Modern machine learning systems increasingly rely on sensitive data, creating significant privacy, security, and regulatory risks that existing privacy-preserving machine learning (ppML) techniques, such as Differential Privacy (DP) and…
Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to…
Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is…