Related papers: Perception-in-the-Loop Adversarial Examples

When solving optimization problems with black-box approaches, the algorithms gather valuable information about the problem instance during the optimization process. This information is used to adjust the distributions from which new…

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…

We present a developmental framework based on a long-term memory and reasoning mechanisms (Vision Similarity and Bayesian Optimisation). This architecture allows a robot to optimize autonomously hyper-parameters that need to be tuned from…

Deep convolutional neural networks have achieved great successes over recent years, particularly in the domain of computer vision. They are fast, convenient, and -- thanks to mature frameworks -- relatively easy to implement and deploy.…

Given a black-box classification model and an unlabeled evaluation dataset from some application domain, efficient strategies need to be developed to evaluate the model. Random sampling allows a user to estimate metrics like accuracy,…

The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to…

Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies reveal that black-box…

We propose Black Box Explanations through Transparent Approximations (BETA), a novel model agnostic framework for explaining the behavior of any black-box classifier by simultaneously optimizing for fidelity to the original model and…

Bilevel optimization is a field of significant theoretical and practical interest, yet solving such optimization problems remains challenging. Evolutionary methods have been employed to address these problems in the black-box setting;…

Deep neural networks (DNNs) have achieved remarkable success in diverse fields. However, it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings. A large number of black-box attack methods…

We propose a novel genetic-algorithm technique that generates black-box adversarial examples which successfully fool neural network based text classifiers. We perform a genetic search with multi-objective optimization guided by deep…

Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers. In this paper we propose a low-cost…

Proportional integral derivative (PID) controllers are important and widely used tools in system control. Tuning of the controller gains is a laborious task, especially for complex systems such as combustion engines. To minimize the time of…

Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications. These adversarial examples tend to be transferable between models, but targeted…

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science,…

Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a highly effective optimization technique. A primary challenge when applying CMA-ES in high dimensionality is sampling from a multivariate normal distribution with an arbitrary…

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…

In this paper, we explore the properties of loss curvature with respect to input data in deep neural networks. Curvature of loss with respect to input (termed input loss curvature) is the trace of the Hessian of the loss with respect to the…

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…

Machine learning has been proven to be susceptible to carefully crafted samples, known as adversarial examples. The generation of these adversarial examples helps to make the models more robust and gives us an insight into the underlying…