English
Related papers

Related papers: Spanning Attack: Reinforce Black-box Attacks with …

200 papers

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed…

Machine Learning · Computer Science 2019-08-02 Alessio Russo , Alexandre Proutiere

We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning. Theoretically, we revisit the simple Gaussian model of Schmidt et al. that shows a sample complexity gap…

Machine Learning · Statistics 2022-01-14 Yair Carmon , Aditi Raghunathan , Ludwig Schmidt , Percy Liang , John C. Duchi

Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the model. Such methods, although they remain…

Machine Learning · Computer Science 2026-03-13 Anna Chistyakova , Mikhail Pautov

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…

Machine Learning · Computer Science 2019-11-27 Masoumeh Shafieinejad , Jiaqi Wang , Nils Lukas , Xinda Li , Florian Kerschbaum

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a…

Machine Learning · Computer Science 2019-11-25 Yiren Zhao , Ilia Shumailov , Han Cui , Xitong Gao , Robert Mullins , Ross Anderson

One major problem in black-box adversarial attacks is the high query complexity in the hard-label attack setting, where only the top-1 predicted label is available. In this paper, we propose a novel geometric-based approach called Tangent…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Chen Ma , Xiangyu Guo , Li Chen , Jun-Hai Yong , Yisen Wang

While deep neural networks show unprecedented performance in various tasks, the vulnerability to adversarial examples hinders their deployment in safety-critical systems. Many studies have shown that attacks are also possible even in a…

Cryptography and Security · Computer Science 2021-11-09 Junyoung Byun , Hyojun Go , Changick Kim

Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial…

Machine Learning · Computer Science 2018-11-06 Yi Shi , Yalin E. Sagduyu , Kemal Davaslioglu , Jason H. Li

Adversarial attacks on graphs have attracted considerable research interests. Existing works assume the attacker is either (partly) aware of the victim model, or able to send queries to it. These assumptions are, however, unrealistic. To…

Machine Learning · Computer Science 2021-09-01 Jiarong Xu , Yizhou Sun , Xin Jiang , Yanhao Wang , Yang Yang , Chunping Wang , Jiangang Lu

Deep neural networks (DNNs) have been broadly adopted in health risk prediction to provide healthcare diagnoses and treatments. To evaluate their robustness, existing research conducts adversarial attacks in the white/gray-box setting where…

Machine Learning · Computer Science 2021-12-14 Muchao Ye , Junyu Luo , Guanjie Zheng , Cao Xiao , Ting Wang , Fenglong Ma

Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security…

Computation and Language · Computer Science 2024-11-14 Chong Zhang , Mingyu Jin , Dong Shu , Taowen Wang , Dongfang Liu , Xiaobo Jin

Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models. In this paper, we…

Machine Learning · Computer Science 2017-12-29 Arjun Nitin Bhagoji , Warren He , Bo Li , Dawn Song

Transfer learning has become a common practice for training deep learning models with limited labeled data in a target domain. On the other hand, deep models are vulnerable to adversarial attacks. Though transfer learning has been widely…

Machine Learning · Computer Science 2020-08-26 Yinghua Zhang , Yangqiu Song , Jian Liang , Kun Bai , Qiang Yang

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively…

Machine Learning · Computer Science 2021-06-11 Guansong Pang , Anton van den Hengel , Chunhua Shen , Longbing Cao

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

A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute models to generate the perturbation, then apply the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-06 Jing Wu , Mingyi Zhou , Shuaicheng Liu , Yipeng Liu , Ce Zhu

Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoising filters and to…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Ali Shahin Shamsabadi , Ricardo Sanchez-Matilla , Andrea Cavallaro

Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models…

Machine Learning · Computer Science 2019-08-16 Vinod Subramanian , Emmanouil Benetos , Ning Xu , SKoT McDonald , Mark Sandler

We propose the first general-purpose gradient-based attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix,…

Computation and Language · Computer Science 2021-04-29 Chuan Guo , Alexandre Sablayrolles , Hervé Jégou , Douwe Kiela

Object detection has been widely used in many safety-critical tasks, such as autonomous driving. However, its vulnerability to adversarial examples has not been sufficiently studied, especially under the practical scenario of black-box…

Computer Vision and Pattern Recognition · Computer Science 2022-01-25 Siyuan Liang , Baoyuan Wu , Yanbo Fan , Xingxing Wei , Xiaochun Cao