Related papers: Query-Efficient and Scalable Black-Box Adversarial…

A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and…

We introduce a novel distributed derivative-free optimization framework that is resilient to stragglers. The proposed method employs coded search directions at which the objective function is evaluated, and a decoding step to find the next…

Classical adversarial attacks are phrased as a constrained optimisation problem. Despite the efficacy of a constrained optimisation approach to adversarial attacks, one cannot trace how an adversarial point was generated. In this work, we…

This paper concerns corpus poisoning attacks in dense information retrieval, where an adversary attempts to compromise the ranking performance of a search algorithm by injecting a small number of maliciously generated documents into the…

We introduce BayeSQP, a novel algorithm for general black-box optimization that merges the structure of sequential quadratic programming with concepts from Bayesian optimization. BayeSQP employs second-order Gaussian process surrogates for…

The optimization of expensive-to-evaluate black-box functions over combinatorial structures is an ubiquitous task in machine learning, engineering and the natural sciences. The combinatorial explosion of the search space and costly…

We study the problem of attacking video recognition models in the black-box setting, where the model information is unknown and the adversary can only make queries to detect the predicted top-1 class and its probability. Compared with the…

Deep neural networks (DNNs) are shown to be susceptible to adversarial example attacks. Most existing works achieve this malicious objective by crafting subtle pixel-wise perturbations, and they are difficult to launch in the physical world…

Bayesian optimization (BO) is a successful methodology to optimize black-box functions that are expensive to evaluate. While traditional methods optimize each black-box function in isolation, there has been recent interest in speeding up BO…

With further development in the fields of computer vision, network security, natural language processing and so on so forth, deep learning technology gradually exposed certain security risks. The existing deep learning algorithms cannot…

Neural networks are vulnerable to adversarial examples, which are malicious inputs crafted to fool pre-trained models. Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted…

We present a method for adversarial input generation against black box models for reading comprehension based question answering. Our approach is composed of two steps. First, we approximate a victim black box model via model extraction…

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…

We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the semantics and syntax of…

Active policy search combines the trial-and-error methodology from policy search with Bayesian optimization to actively find the optimal policy. First, policy search is a type of reinforcement learning which has become very popular for…

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…

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…

With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of the network and are…

Crafting adversarial examples has become an important technique to evaluate the robustness of deep neural networks (DNNs). However, most existing works focus on attacking the image classification problem since its input space is continuous…

The deployment of large-scale generative models is often restricted by their potential risk of causing harm to users in unpredictable ways. We focus on the problem of black-box red teaming, where a red team generates test cases and…