Related papers: Boundary on the Table: Efficient Black-Box Decisio…
Adversarial examples represent a serious issue for the application of machine learning models in many sensitive domains. For generating adversarial examples, decision based black-box attacks are one of the most practical techniques as they…
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query…
The susceptibility of deep neural networks (DNNs) to adversarial examples has prompted an increase in the deployment of adversarial attacks. Image-agnostic universal adversarial perturbations (UAPs) are much more threatening, but many…
Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. For white-box attack, optimization-based attack algorithms such as projected gradient descent…
Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected…
Adversarial attacks are a major concern in security-centered applications, where malicious actors continuously try to mislead Machine Learning (ML) models into wrongly classifying fraudulent activity as legitimate, whereas system…
Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has…
Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life…
CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models'…
Binary analyses based on deep neural networks (DNNs), or neural binary analyses (NBAs), have become a hotly researched topic in recent years. DNNs have been wildly successful at pushing the performance and accuracy envelopes in the natural…
Adversarial examples are known as carefully perturbed images fooling image classifiers. We propose a geometric framework to generate adversarial examples in one of the most challenging black-box settings where the adversary can only…
With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the…
Numerous works study black-box attacks on image classifiers. However, these works make different assumptions on the adversary's knowledge and current literature lacks a cohesive organization centered around the threat model. To systematize…
Deep learning has demonstrated state-of-the-art performance for a variety of challenging computer vision tasks. On one hand, this has enabled deep visual models to pave the way for a plethora of critical applications like disease…
Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized by querying the target model, or a transfer-based approach…
Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…
Adversarial attack has garnered considerable attention due to its profound implications for the secure deployment of robots in sensitive security scenarios. To potentially push for advances in the field, this paper studies the adversarial…
Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial…
Adversarial attack reveals the vulnerability of deep learning models. It is assumed that high curvature may give rise to rough decision boundary and thus result in less robust models. However, the most commonly used \textit{curvature} is…
Since Biggio et al. (2013) and Szegedy et al. (2013) first drew attention to adversarial examples, there has been a flood of research into defending and attacking machine learning models. However, almost all proposed attacks assume…