Related papers: Investigating White-Box Attacks for On-Device Mode…
To launch black-box attacks against a Deep Neural Network (DNN) based Face Recognition (FR) system, one needs to build \textit{substitute} models to simulate the target model, so the adversarial examples discovered from substitute models…
Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model. Recently, white-box model inversion attacks leveraging Generative Adversarial…
Black-box attacks can generate adversarial examples without accessing the parameters of target model, largely exacerbating the threats of deployed deep neural networks (DNNs). However, previous works state that black-box attacks fail to…
Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by…
Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…
Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by poisoning the training dataset, whose intention is to make…
On-device deep learning (DL) has rapidly gained adoption in mobile apps, offering the benefits of offline model inference and user privacy preservation over cloud-based approaches. However, it inevitably stores models on user devices,…
While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and…
Box-free model watermarking is an emerging technique to safeguard the intellectual property of deep learning models, particularly those for low-level image processing tasks. Existing works have verified and improved its effectiveness in…
A significant number of machine learning models are vulnerable to model extraction attacks, which focus on stealing the models by using specially curated queries against the target model. This task is well accomplished by using part of the…
In this paper, we investigate the impact of adversarial attacks on the explainability of deep learning models, which are commonly criticized for their black-box nature despite their capacity for autonomous feature extraction. This black-box…
Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…
Despite their impressive performance, deep visual models are susceptible to transferable black-box adversarial attacks. Principally, these attacks craft perturbations in a target model-agnostic manner. However, surprisingly, we find that…
Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include…
State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on inputs with predefined triggers while retaining performance…
The emergence of deep learning models has revolutionized various industries over the last decade, leading to a surge in connected devices and infrastructures. However, these models can be tricked into making incorrect predictions with high…
Decision-based attacks construct adversarial examples against a machine learning (ML) model by making only hard-label queries. These attacks have mainly been applied directly to standalone neural networks. However, in practice, ML models…
The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule…
Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…
Deep neural networks are widely used in various fields because of their powerful performance. However, recent studies have shown that deep learning models are vulnerable to adversarial attacks, i.e., adding a slight perturbation to the…