English
Related papers

Related papers: Sign-OPT: A Query-Efficient Hard-label Adversarial…

200 papers

Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. For white-box attack, optimization-based attack algorithms such as projected gradient descent…

Machine Learning · Computer Science 2019-09-17 Jinghui Chen , Dongruo Zhou , Jinfeng Yi , Quanquan Gu

Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations. Despite…

Computer Vision and Pattern Recognition · Computer Science 2019-12-06 Pu Zhao , Sijia Liu , Pin-Yu Chen , Nghia Hoang , Kaidi Xu , Bhavya Kailkhura , Xue Lin

Adversarial machine learning is an emerging area showing the vulnerability of deep learning models. Exploring attack methods to challenge state of the art artificial intelligence (A.I.) models is an area of critical concern. The reliability…

Computer Vision and Pattern Recognition · Computer Science 2022-08-31 Samet Bayram , Kenneth Barner

Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial…

Machine Learning · Computer Science 2024-06-13 Feiyang Wang , Xingquan Zuo , Hai Huang , Gang Chen

Adversarial text attack research is useful for testing the robustness of NLP models, however, the rise of transformers has greatly increased the time required to test attacks. Especially when researchers do not have access to adequate…

Cryptography and Security · Computer Science 2024-12-17 Shatarupa Ghosh , Jonathan Rusert

Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that…

Computer Vision and Pattern Recognition · Computer Science 2019-12-23 Ali Mottaghi , Serena Yeung

Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more…

Computer Vision and Pattern Recognition · Computer Science 2018-07-12 Andrew Ilyas , Logan Engstrom , Anish Athalye , Jessy Lin

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…

Computation and Language · Computer Science 2020-12-29 Sachin Saxena

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization~(BO) to specifically…

Machine Learning · Computer Science 2019-10-01 Satya Narayan Shukla , Anit Kumar Sahu , Devin Willmott , J. Zico Kolter

Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected…

Machine Learning · Computer Science 2026-05-26 Florent Tariolle , Florian Yger

Adversarial training (AT) is a widely recognized defense mechanism to gain the robustness of deep neural networks against adversarial attacks. It is built on min-max optimization (MMO), where the minimizer (i.e., defender) seeks a robust…

Machine Learning · Computer Science 2022-10-06 Yihua Zhang , Guanhua Zhang , Prashant Khanduri , Mingyi Hong , Shiyu Chang , Sijia Liu

Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are…

Cryptography and Security · Computer Science 2018-07-25 Kevin Eykholt , Ivan Evtimov , Earlence Fernandes , Bo Li , Dawn Song , Tadayoshi Kohno , Amir Rahmati , Atul Prakash , Florian Tramer

Deep neural networks and other machine learning systems, despite being extremely powerful and able to make predictions with high accuracy, are vulnerable to adversarial attacks. We proposed the DeltaBound attack: a novel, powerful attack in…

Machine Learning · Computer Science 2022-10-04 Lorenzo Rossi

Despite the huge success of Deep Neural Networks (DNNs) in a wide spectrum of machine learning and data mining tasks, recent research shows that this powerful tool is susceptible to maliciously crafted adversarial examples. Up until now,…

Cryptography and Security · Computer Science 2020-02-07 Zhuanghua Liu , Ivor W. Tsang

We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget,…

Machine Learning · Computer Science 2019-08-16 Chuan Guo , Jacob R. Gardner , Yurong You , Andrew Gordon Wilson , Kilian Q. Weinberger

Adversarial attacks have the potential to mislead deep neural network classifiers by introducing slight perturbations. Developing algorithms that can mitigate the effects of these attacks is crucial for ensuring the safe use of artificial…

Machine Learning · Computer Science 2023-10-31 Boya Zhang , Weijian Luo , Zhihua Zhang

Existing score-based adversarial attacks mainly focus on crafting $top$-1 adversarial examples against classifiers with single-label classification. Their attack success rate and query efficiency are often less than satisfactory,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Md Farhamdur Reza , Richeng Jin , Tianfu Wu , Huaiyu Dai

There has been recently a growing interest in studying adversarial examples on natural language models in the black-box setting. These methods attack natural language classifiers by perturbing certain important words until the classifier…

Machine Learning · Computer Science 2021-05-04 Mahmoud Hossam , Trung Le , He Zhao , Viet Huynh , Dinh Phung

As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought.…

Researchers have repeatedly shown that it is possible to craft adversarial attacks on deep classifiers (small perturbations that significantly change the class label), even in the "black-box" setting where one only has query access to the…

Machine Learning · Computer Science 2021-02-02 Devin Willmott , Anit Kumar Sahu , Fatemeh Sheikholeslami , Filipe Condessa , Zico Kolter