相关论文: Opportunistic Target Selection: Early Directional …

Deep neural networks are facing severe threats from adversarial attacks. Most existing black-box attacks fool target model by generating either global perturbations or local patches. However, both global perturbations and local patches…

Many machine learning systems make constrained decisions by optimizing factorized objectives, but the context-specific objective is often treated as fixed. We study contextual decision-weight learning: from logged decisions and proxy…

We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or…

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of…

Adversarial perturbations are a useful way to expose vulnerabilities in object detectors. Existing perturbation methods are frequently white-box, architecture specific and use a loss function. More importantly, while they are often…

Recent studies unveil the vulnerabilities of deep ranking models, where an imperceptible perturbation can trigger dramatic changes in the ranking result. While previous attempts focus on manipulating absolute ranks of certain candidates,…

While image-to-text models have demonstrated significant advancements in various vision-language tasks, they remain susceptible to adversarial attacks. Existing white-box attacks on image-to-text models require access to the architecture,…

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label~(hard label) to a queried data input. We propose a…

In this paper, we study oracle-efficient algorithms for beyond worst-case analysis of online learning. We focus on two settings. First, the smoothed analysis setting of [RST11,HRS22] where an adversary is constrained to generating samples…

Adversarial machine learning is an emerging area showing the vulnerability of deep learning models. Exploring attack methods to challenge state of the art artificial intelligence (A.I.) models is an area of critical concern. The reliability…

Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models. In this paper, we…

We propose the Square Attack, a score-based black-box $l_2$- and $l_\infty$-adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. Square Attack is based on a randomized search…

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 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…

We study the problem of offline policy optimization in stochastic contextual bandit problems, where the goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. Rather than making…

We focus on the problem of adversarial attacks against models on discrete sequential data in the black-box setting where the attacker aims to craft adversarial examples with limited query access to the victim model. Existing black-box…

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…

We present a new method for score-based adversarial attack, where the attacker queries the loss-oracle of the target model. Our method employs a parameterized search space with a structure that captures the relationship of the gradient of…