Results 41 to 50 of about 880 (115)
Defensive Dual Masking for Robust Adversarial Defense
Computational LinguisticsAbstract Adversarial defenses for textual data have gained considerable attention in recent years due to the increasing vulnerability of Natural Language Processing (NLP) models to adversarial attacks. These attacks exploit subtle perturbations in input text to deceive models, posing significant challenges to model robustness and ...
Wangli Yang +3 more
openaire +2 more sources
Towards Adversarial Robustness for Multi-Mode Data through Metric Learning
Sensors, 2023 Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial ...
Sarwar Khan +3 more
doaj +1 more source
Survey on adversarial attacks and defenses for object detection
Tongxin xuebao, 2023 In response to recent developments in adversarial attacks and defenses for object detection, relevant terms and concepts associated with object detection and adversarial learning were first introduced.Subsequently, according to the evolution process of ...
Xinxin WANG +6 more
doaj +2 more sources
Adversarial Attack and Defense on Deep Neural Network-Based Voice Processing Systems: An Overview
Applied Sciences, 2021 Voice Processing Systems (VPSes), now widely deployed, have become deeply involved in people’s daily lives, helping drive the car, unlock the smartphone, make online purchases, etc.
Xiaojiao Chen, Sheng Li, Hao Huang
doaj +1 more source
A Mask-Based Adversarial Defense Scheme
Algorithms, 2022 Adversarial attacks hamper the functionality and accuracy of deep neural networks (DNNs) by meddling with subtle perturbations to their inputs. In this work, we propose a new mask-based adversarial defense scheme (MAD) for DNNs to mitigate the negative ...
Weizhen Xu +3 more
doaj +1 more source
Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong
CoRR, 2017 Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a strong defense can be created by combining multiple (possibly weak) defenses. To answer this question, we study three defenses that follow this approach. Two of these are recently
Warren He +4 more
openaire +3 more sources
Defense-VAE: A Fast and Accurate Defense Against Adversarial Attacks [PDF]
, 2020 Deep neural networks (DNNs) have been enormously successful across a variety of prediction tasks. However, recent research shows that DNNs are particularly vulnerable to adversarial attacks, which poses a serious threat to their applications in security-sensitive systems.
Xiang Li 0080, Shihao Ji 0001
openaire +2 more sources
Complex & Intelligent SystemsNeural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absence of reliance on the target model
Xinlei Liu +6 more
doaj +1 more source
You Can’t Fool All the Models: Detect Adversarial Samples via Pruning Models
IEEE Access, 2021 Many adversarial attack methods have investigated the security issue of deep learning models. Previous works on detecting adversarial samples show superior in accuracy but consume too much memory and computing resources.
Renxuan Wang +3 more
doaj +1 more source
Efficient Defenses Against Adversarial Attacks [PDF]
Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, 2017 Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the
Valentina Zantedeschi +2 more
openaire +2 more sources