Related papers: On the Importance of Encrypting Deep Features
Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…
Inverse scattering aims to infer information about a hidden object by using the received scattered waves and training data collected from forward mathematical models. Recent advances in computing have led to increasing attention towards…
Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images. The robustness of existing defenses suffers greatly under white-box attack settings, where an adversary…
Model inversion (MI) attacks aim to infer and reconstruct private training data by abusing access to a model. MI attacks have raised concerns about the leaking of sensitive information (e.g. private face images used in training a face…
The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…
Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…
Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…
Deep neural networks are vulnerable to adversarial attacks and hard to interpret because of their black-box nature. The recently proposed invertible network is able to accurately reconstruct the inputs to a layer from its outputs, thus has…
In this paper, we propose a novel generative model-based attack on learnable image encryption methods proposed for privacy-preserving deep learning. Various learnable encryption methods have been studied to protect the sensitive visual…
The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particularly model inversion (MI) attacks, posing a significant…
Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…
We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the…
Model inversion (MI) attacks allow to reconstruct average per-class representations of a machine learning (ML) model's training data. It has been shown that in scenarios where each class corresponds to a different individual, such as face…
In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…
Backend enrichment is now widely deployed in sensitive domains such as product recommendation pipelines, healthcare, and finance, where models are trained on confidential data and retrieve private features whose values influence inference…
Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…
Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…
There is growing concern about how personal data are used when users grant applications direct access to the sensors of their mobile devices. In fact, high resolution temporal data generated by motion sensors reflect directly the activities…
Facially manipulated images and videos or DeepFakes can be used maliciously to fuel misinformation or defame individuals. Therefore, detecting DeepFakes is crucial to increase the credibility of social media platforms and other media…
In this work we introduce a new protocol for vector aggregation in the context of the Shuffle Model, a recent model within Differential Privacy (DP). It sits between the Centralized Model, which prioritizes the level of accuracy over the…