相关论文: Opportunistic Target Selection: Early Directional …

Adversarial attacks often involve random perturbations of the inputs drawn from uniform or Gaussian distributions, e.g., to initialize optimization-based white-box attacks or generate update directions in black-box attacks. These simple…

Few-Shot classification aims at solving problems that only a few samples are available in the training process. Due to the lack of samples, researchers generally employ a set of training tasks from other domains to assist the target task,…

Adversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a novel black-box, decision-based adversarial attack tailored for tabular data. Our approach…

Supervised learning models are challenged by the intrinsic complexities of training data such as outliers and minority subpopulations and intentional attacks at inference time with adversarial samples. While traditional robust learning…

Recent adversarial defense approaches have failed. Untargeted gradient-based attacks cause classifiers to choose any wrong class. Our novel white-box defense tricks untargeted attacks into becoming attacks targeted at designated target…

We study the problem of generating adversarial examples in a black-box setting in which only loss-oracle access to a model is available. We introduce a framework that conceptually unifies much of the existing work on black-box attacks, and…

Existing adversarial attacks often neglect perturbation sparsity, limiting their ability to model structural changes and to explain how deep neural networks (DNNs) process meaningful input patterns. We propose ATOS (Attack Through…

Trajectory prediction systems are critical for autonomous vehicle safety, yet remain vulnerable to adversarial attacks that can cause catastrophic traffic behavior misinterpretations. Existing attack methods require white-box access with…

We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $\ell_\infty$ and $\ell_2$ metrics, where only loss-oracle access to the model is available. On two public…

Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly…

Recent work has proposed stateful defense models (SDMs) as a compelling strategy to defend against a black-box attacker who only has query access to the model, as is common for online machine learning platforms. Such stateful defenses aim…

We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for generating adversarial examples, where limited model queries are…

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 learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples. In this work, we consider the practical and challenging decision-based black-box…

We introduce a new black-box attack achieving state of the art performances. Our approach is based on a new objective function, borrowing ideas from $\ell_\infty$-white box attacks, and particularly designed to fit derivative-free…

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…

Adversarial attacks perturb images such that a deep neural network produces incorrect classification results. A promising approach to defend against adversarial attacks on natural multi-object scenes is to impose a context-consistency…

Generating adversarial examples in a black-box setting retains a significant challenge with vast practical application prospects. In particular, existing black-box attacks suffer from the need for excessive queries, as it is non-trivial to…

Transfer-based targeted adversarial attacks against black-box deep neural networks (DNNs) have been proven to be significantly more challenging than untargeted ones. The impressive transferability of current SOTA, the generative methods,…

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…