Related papers: White-Box Adversarial Defense via Self-Supervised …
Adversarial attacks on deep learning models have compromised their performance considerably. As remedies, a lot of defense methods were proposed, which however, have been circumvented by newer attacking strategies. In the midst of this…
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input,…
From face recognition systems installed in phones to self-driving cars, the field of AI is witnessing rapid transformations and is being integrated into our everyday lives at an incredible pace. Any major failure in these system's…
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 example attacks have emerged as a critical threat to machine learning. Adversarial attacks in image classification abuse various, minor modifications to the image that confuse the image classification neural network -- while the…
Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the…
Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However,…
Adversarial reprogramming allows stealing computational resources by repurposing machine learning models to perform a different task chosen by the attacker. For example, a model trained to recognize images of animals can be reprogrammed to…
Deep learning-based object detection has become ubiquitous in the last decade due to its high accuracy in many real-world applications. With this growing trend, these models are interested in being attacked by adversaries, with most of the…
Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong label. Since machine-learning is being deployed in…
Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade…
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…
The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise the performance of deep learning models by reducing output confidence or inducing…
There are two main attack models considered in the adversarial robustness literature: black-box and white-box. We consider these threat models as two ends of a fine-grained spectrum, indexed by the number of queries the adversary can ask.…
We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Specifically, we experiment with low-pass filtering, PCA, JPEG…
Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…
Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human…
Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…
Many deep neural networks are susceptible to minute perturbations of images that have been carefully crafted to cause misclassification. Ideally, a robust classifier would be immune to small variations in input images, and a number of…
In a membership inference attack, an attacker aims to infer whether a data sample is in a target classifier's training dataset or not. Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier,…