Related papers: Biometric Backdoors: A Poisoning Attack Against Un…
The proliferation of online biometric authentication has necessitated security requirements of biometric templates. The existing secure biometric authentication schemes feature a server-centric model, where a service provider maintains a…
Machine learning is susceptible to poisoning attacks, in which an attacker controls a small fraction of the training data and chooses that data with the goal of inducing some behavior unintended by the model developer in the trained model.…
As the capacity of deep neural networks (DNNs) increases, their need for huge amounts of data significantly grows. A common practice is to outsource the training process or collect more data over the Internet, which introduces the risks of…
With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize…
Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…
Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…
Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…
Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning…
Machine learning (ML) models trained on data from potentially untrusted sources are vulnerable to poisoning. A small, maliciously crafted subset of the training inputs can cause the model to learn a "backdoor" task (e.g., misclassify inputs…
The increased need for unattended authentication in multiple scenarios has motivated a wide deployment of biometric systems in the last few years. This has in turn led to the disclosure of security concerns specifically related to biometric…
Applications based on biometric authentication have received a lot of interest in the last years due to the breathtaking results obtained using personal traits such as face or fingerprint. However, it is important not to forget that these…
Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…
Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose Neural Fingerprinting, a simple, yet effective method to detect adversarial examples by verifying…
Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…
We assess the security of machine learning based biometric authentication systems against an attacker who submits uniform random inputs, either as feature vectors or raw inputs, in order to find an accepting sample of a target user. The…
In this paper we address the issues of using edge detection techniques on facial images to produce cancellable biometric templates and a novel method for template verification against tampering. With increasing use of biometrics, there is a…
Transfer learning (TL) has been widely used in electroencephalogram (EEG)-based brain-computer interfaces (BCIs) for reducing calibration efforts. However, backdoor attacks could be introduced through TL. In such attacks, an attacker embeds…
With the advancement of AI generative techniques, Deepfake faces have become incredibly realistic and nearly indistinguishable to the human eye. To counter this, Deepfake detectors have been developed as reliable tools for assessing face…
Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…
Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of…