23 papers · ranked by Valyu relevance
Kaleel Mahmood, Deniz Gurevin, Marten van Dijk, Phuoung Ha Nguyen + 1 more
'Luis Hernández-Callejo'] Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the analyses of these defenses to include adaptive black-box…
Kaleel Mahmood, Deniz Gurevin, Marten van Dijk, Phuoung Ha Nguyen
Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the analysis of these defenses to include adaptive black-box adversaries. Our evaluation is…
Han Cao, Chengxiang Si, Qindong Sun, Yanxiao Liu + 3 more
'Prosanta Gope' 'Gholamreza Anbarjafari'] The vulnerability of deep neural network (DNN)-based systems makes them susceptible to adversarial perturbation and may cause classification task failure. In this work, we propose an adversarial attack model using the Artificial Bee Colony (ABC) algorithm to generate…
Mohammed Alkhowaiter, Hisham Kholidy, Mnassar A. Alyami, Abdulmajeed Alghamdi + 2 more
'Abdulmajeed Alghamdi' 'Cliff Zou' 'Hai Dong'] Deep learning models have been used in creating various effective image classification applications. However, they are vulnerable to adversarial attacks that seek to misguide the models into predicting incorrect classes. Our study of major adversarial attack models shows…
Pengfei Xie, Shuhao Shi, Shuai Yang, Kai Qiao + 5 more
'Linyuan Wang' 'Jian Chen' 'Guoen Hu' 'Bin Yan'] Deep neural networks (DNNs) are proven vulnerable to attack against adversarial examples. Black-box transfer attacks pose a massive threat to AI applications without accessing target models. At present, the most effective black-box attack methods mainly adopt data…
Narmin Ghaffari Laleh, Daniel Truhn, Gregory Patrick Veldhuizen, Tianyu Han + 7 more
Artificial Intelligence (AI) can support diagnostic workflows in oncology by aiding diagnosis and providing biomarkers. AI applications are therefore expected to evolve from academic prototypes to commercial products in the coming years. However, AI applications are vulnerable to adversarial attacks, such as malicious…
Shashank Kotyan
—Deep Learning has empowered us to train neural networks for complex data with high performance. However, with the growing research, several vulnerabilities in neural networks have been exposed. A particular branch of research, Adversarial Machine Learning, exploits and understands some of the vulnerabilities that…
Linnea Evanson, Maksim Lavrov, Iakov Kharitonov, Sihao Lu + 1 more
Object recognition by natural and artificial sensory systems requires a combination of selectivity and invariance. Both natural and artificial neural networks achieve selectivity and invariance by propagating sensory information though layers of neurons organised in a functional hierarchy. Both employ computational…
Zhibo Jin, Jilei Zhang, Zhiyu Zhu, Huaming Chen
—The robustness of deep learning models against adversarial attacks remains a pivotal concern. This study presents, for the first time, an exhaustive review of the transferability aspect of adversarial attacks. It systematically categorizes and critically evaluates various methodologies developed to augment the…
Mouna Rabhi, Roberto Di Pietro
Adversarial attacks on deep neural models pose a serious threat to their reliability and security. Existing defense mechanisms are often narrow in focus, addressing a specific type of attack, or being vulnerable to sophisticated attacks. In this paper, we propose a new defense mechanism that, while being focused on…
John Harshith, Mantej Singh Gill, Madhan Jothimani
There have been recent adversarial attacks that are difficult to find. These new adversarial attacks methods may pose challenges to current deep learning cyber defense systems and could influence the future defense of cyberattacks. The authors focus on this domain in this research paper. They explore the consequences…
Yang Wang, Ang Li, Zhen Yang, Xunyun Liu + 1 more
Transformer-based detectors have demonstrated exceptional accuracy in visible-object detection tasks. However, adversarial patches, specific types of adversarial examples, can disrupt these detectors by introducing unrestricted perturbations into specific image regions. Traditional methodologies focus on placing…
Jin-Tao Yang, Hao Jiang, Hao Li, Dong-Sheng Ye + 4 more
'Andrea Prati' 'Luis Javier García Villalba' 'Vincent A. Cicirello'] Adversarial examples present a severe threat to deep neural networks’ application in safetycritical domains such as autonomous driving. Although there are numerous defensive solutions, they all have some flaws, such as the fact that they can only…
Roey Bokobza, Yisroel Mirsky
Adversarial Attacks Authors: ['Roey Bokobza' 'Yisroel Mirsky'] Abstract. Our paper presents a novel defence against black box attacks, where attackers use the victim model as an oracle to craft their adversarial examples. Unlike traditional preprocessing defences that rely on sanitizing input samples, our stateless…
Jenelle Feather, Guillaume Leclerc, Aleksander Mądry, Josh H. McDermott
Deep neural network models of sensory systems are often proposed to learn representational transformations with invariances like those in the brain. To reveal these invariances we generated “model metamers” – stimuli whose activations within a model stage are matched to those of a natural stimulus. Metamers for…
Viet Tien Pham, Minh Hieu Ha, Bao V. Q. Bui, Truong Son Hy
Accurate and reliable medical image segmentation is essential for computer-aided diagnosis and formulating appropriate treatment plans. However, real-world challenges such as suboptimal image quality and computational resource constraints hinder the effective deployment of deep learning-based segmentation models. To…
Francisco Durán, Silverio Martínez-Fernández, Michael Felderer, Xavier Franch + 1 more
'Xavier Franch' 'Shibiao Wan'] Background When using deep learning models, one of the most critical vulnerabilities is their exposure to adversarial inputs, which can cause wrong decisions (e.g., incorrect classification of an image) with minor perturbations. To address this vulnerability, it becomes necessary to…
Yulong Wang, Tong Sun, Shenghong Li, Xin Yuan + 3 more
'Ekram Hossain' 'H. Vincent Poor'] Abstract—Adversarial attacks and defenses in machine learning and deep neural network have been gaining significant attention due to the rapidly growing applications of deep learning in the Internet and relevant scenarios. This survey provides a comprehensive overview of the recent…
Daniel Mas Montserrat, Alexander G. Ioannidis
Adversarial attacks can drastically change the output of a method by performing a small change on its input. While they can be a useful framework to analyze worst-case robustness, they can also be used by malicious agents to perform damage in machine learning-based applications. The proliferation of platforms that…
Zhe Li, Josue Ortega Caro, Evgenia Rusak, Wieland Brendel + 5 more
Machine learning models have difficulty generalizing to data outside of the distribution they were trained on. In particular, vision models are usually vulnerable to adversarial attacks or common corruptions, to which the human visual system is robust. Recent studies have found that regularizing machine learning models…
Authors not listed
Predicting reaction yields in synthetic chemistry remains a significant challenge. This study systematically evaluates the impact of tokenization, molecular representation, pre-training data, and adversarial training on a BERT-based model for yield prediction of Buchwald-Hartwig and Suzuki-Miyaura coupling reactions…
Nathan Mancheun Lui, Max D Li, Matthew Ford
Deep generative models for molecular graphs offer a new avenue for property optimization in drug discovery. Optimizing differentiable models that generate molecular graphs is certainly faster, cheaper, and much more accessible than traditional methods of chemical synthesis. Recent advances in generative modeling have…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…