相关论文: Post-train Black-box Defense via Bayesian Boundary…

Adversarial robustness poses a critical challenge in the deployment of deep learning models for real-world applications. Traditional approaches to adversarial training and supervised detection rely on prior knowledge of attack types and…

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…

Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…

Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based services offered by…

Currently, various uncertainty quantification methods have been proposed to provide certainty and probability estimates for deep learning models' label predictions. Meanwhile, with the growing demand for the right to be forgotten, machine…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

It is known that deep neural networks, trained for the classification of non-sensitive target attributes, can reveal sensitive attributes of their input data through internal representations extracted by the classifier. We take a step…

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations.…

Deep neural networks are susceptible to adversarial inputs and various methods have been proposed to defend these models against adversarial attacks under different perturbation models. The robustness of models to adversarial attacks has…

Hyperbox-based classification has been seen as a promising technique in which decisions on the data are represented as a series of orthogonal, multidimensional boxes (i.e., hyperboxes) that are often interpretable and human-readable.…

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the…

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…

This study investigates behavior-targeted attacks on reinforcement learning and their countermeasures. Behavior-targeted attacks aim to manipulate the victim's behavior as desired by the adversary through adversarial interventions in state…

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Deep Neural Networks have recently gained lots of success after enabling several breakthroughs in notoriously challenging problems. Training these networks is computationally expensive and requires vast amounts of training data. Selling…

Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…

Deep neural networks face persistent challenges in defending against backdoor attacks, leading to an ongoing battle between attacks and defenses. While existing backdoor defense strategies have shown promising performance on reducing attack…

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,…

Reinforcement Learning (RL) has demonstrated state-of-the-art results in a number of autonomous system applications, however many of the underlying algorithms rely on black-box predictions. This results in poor explainability of the…