English
Related papers

Related papers: Attack Graph Obfuscation

200 papers

Adversarial attacks on Graph Neural Networks aim to perturb the performance of the learner by carefully modifying the graph topology and node attributes. Existing methods achieve attack stealthiness by constraining the modification budget…

Machine Learning · Computer Science 2025-06-10 Kai Yuan , Jiahao Zhang , Yidi Wang , Xiaobing Pei

As Graph Neural Networks (GNNs) become increasingly prevalent in a variety of fields, from social network analysis to protein-protein interaction studies, growing concerns have emerged regarding the unauthorized utilization of personal…

Cryptography and Security · Computer Science 2023-10-12 Yixin Liu , Chenrui Fan , Xun Chen , Pan Zhou , Lichao Sun

Identifying shortest paths between nodes in a network is an important task in many applications. Recent work has shown that a malicious actor can manipulate a graph to make traffic between two nodes of interest follow their target path. In…

Social and Information Networks · Computer Science 2025-05-01 Benjamin A. Miller , Zohair Shafi , Wheeler Ruml , Yevgeniy Vorobeychik , Tina Eliassi-Rad , Scott Alfeld

We implemented and evaluated an automated cyber defense agent. The agent takes security alerts as input and uses reinforcement learning to learn a policy for executing predefined defensive measures. The defender policies were trained in an…

Cryptography and Security · Computer Science 2023-04-24 Jakob Nyberg , Pontus Johnson

Traffic analysis is a type of attack on secure communications systems, in which the adversary extracts useful patterns and information from the observed traffic. This paper improves and extends an efficient traffic analysis attack, called…

Cryptography and Security · Computer Science 2017-10-03 Navid Emamdoost , Mohammad Sadeq Dousti , Rasool Jalili

Social networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks and understanding the vulnerabilities is critical to rumor detection in…

Machine Learning · Computer Science 2022-10-17 Yuefei Lyu , Xiaoyu Yang , Jiaxin Liu , Philip S. Yu , Sihong Xie , Xi Zhang

Recent research has revealed that Graph Neural Networks (GNNs) are susceptible to adversarial attacks targeting the graph structure. A malicious attacker can manipulate a limited number of edges, given the training labels, to impair the…

Machine Learning · Computer Science 2023-03-30 Zihan Liu , Ge Wang , Yun Luo , Stan Z. Li

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…

Machine Learning · Computer Science 2019-11-26 Arjun Nitin Bhagoji , Supriyo Chakraborty , Prateek Mittal , Seraphin Calo

Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious concerns, especially when dealing with sensitive information. Local Differential Privacy…

Machine Learning · Computer Science 2026-03-24 Matta Varun , Ajay Kumar Dhakar , Yuan Hong , Shamik Sural

Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-09-07 Uriya Pesso , Koby Bibas , Meir Feder

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…

Machine Learning · Computer Science 2023-02-28 You Qiaoben , Chengyang Ying , Xinning Zhou , Hang Su , Jun Zhu , Bo Zhang

Social network analysis tools can infer various attributes just by scrutinizing one's connections. Several researchers have studied the problem faced by an evader whose goal is to strategically rewire their social connections in order to…

Physics and Society · Physics 2021-07-29 Marcin Waniek , Petter Holme , Talal Rahwan

Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. This vulnerability has spurred a growing focus on designing…

Machine Learning · Computer Science 2025-05-27 Tao Wu , Canyixing Cui , Xingping Xian , Shaojie Qiao , Chao Wang , Lin Yuan , Shui Yu

A plethora of attack methods have been proposed to generate adversarial examples, among which the iterative methods have been demonstrated the ability to find a strong attack. However, the computation of an adversarial perturbation for a…

Machine Learning · Computer Science 2021-12-16 Chia-Hung Yuan , Pin-Yu Chen , Chia-Mu Yu

While most security projects have focused on fending off attacks coming from outside the organizational boundaries, a real threat has arisen from the people who are inside those perimeter protections. Insider threats have shown their power…

Cryptography and Security · Computer Science 2018-09-05 Anagi Gamachchi , Li Sun , Serdar Boztas

Graph generative diffusion models have recently emerged as a powerful paradigm for generating complex graph structures, effectively capturing intricate dependencies and relationships within graph data. However, the privacy risks associated…

Machine Learning · Computer Science 2026-01-08 Xiuling Wang , Xin Huang , Guibo Luo , Jianliang Xu

We introduce the novel problem of benchmarking fraud detectors on private graph-structured data. Currently, many types of fraud are managed in part by automated detection algorithms that operate over graphs. We consider the scenario where a…

Cryptography and Security · Computer Science 2025-07-31 Alexander Goldberg , Giulia Fanti , Nihar Shah , Zhiwei Steven Wu

Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work, we exploit an overlooked property of adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Yaoteng Tan , Zikui Cai , M. Salman Asif

Data collected nowadays by social-networking applications create fascinating opportunities for building novel services, as well as expanding our understanding about social structures and their dynamics. Unfortunately, publishing…

Databases · Computer Science 2016-11-11 Paolo Boldi , Francesco Bonchi , Aris Gionis , Tamir Tassa

Advanced Persistent Threats (APTs) are a main impendence in cyber security of computer networks. In 2015, a successful breach remains undetected 146 days on average, reported by [Fi16].With our work we demonstrate a feasible and fast way to…

Databases · Computer Science 2018-02-02 Timo Schindler