A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection
[article]
2022
arXiv
pre-print
Preserved Fulltext
Consequently, the link prediction model trained on the backdoored dataset will predict the link with trigger to the target state. ...
Specifically, the Link-Backdoor combines the fake nodes with the nodes of the target link to form a trigger. Moreover, it optimizes the trigger by the gradient information from the target model. ...
For RQ6, redfrom the fact that Link-Backdoor achieved the average ASR (47.74%) on non-GNNs methods, we can conclude that Link-Backdoor can implement attacks on non-GNNs link prediction methods by gradient ...
arXiv:2208.06776v1
fatcat:fasqmnntu5gl7no4ntmqubrfqq
Embracing Graph Neural Networks for Hardware Security (Invited Paper)
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this survey, we first provide a comprehensive overview of the usage of GNNs in hardware security and propose the first taxonomy to divide the state-of-the-art GNN-based hardware security systems into ...
four categories: (i) HT detection systems, (ii) IP piracy detection systems, (iii) reverse engineering platforms, and (iv) attacks on logic locking. ...
Link prediction can be used for 2 . ...
arXiv:2208.08554v1
fatcat:hxixd6a4vjeyzpszaaljvemagm
Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Graph neural network (GNN) with a powerful representation capability has been widely applied to various areas, such as biological gene prediction, social recommendation, etc. ...
Most of the proposed studies launch the backdoor attack using a trigger that either is the randomly generated subgraph (e.g., erdős-rényi backdoor) for less computational burden, or the gradient-based ...
Blue links: the target link to be predicted. Orange links: the structure of the trigger by the Motif-Backdoor. ...
arXiv:2210.13710v1
fatcat:6yuirzxcjzce7feqdvidasecui
A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
For each aspect, we give the taxonomy of the related methods and formulate the general frameworks for the multiple categories of trustworthy GNNs. ...
Due to their great ability in modeling graph-structured data, GNNs are vastly used in various applications, including high-stakes scenarios such as financial analysis, traffic predictions, and drug discovery ...
This can be viewed as an extension of statistical parity for link prediction. ...
arXiv:2204.08570v2
fatcat:sexh7tl3nfc6vl2porhfxcai54
Deep Learning to Predict the Feasibility of Priority-Based Ethernet Network Configurations
2021
ACM Transactions on Cyber-Physical Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Machine learning has been recently applied in real-time systems to predict whether Ethernet network configurations are feasible in terms of meeting deadline constraints without executing conventional schedulability ...
An evaluation on heterogeneous testing sets comprising realistic automotive networks shows that ensembles of 32 GNN models feature a prediction accuracy ranging from 79.3% to 90% for Ethernet networks ...
the Credit-Based Shaper (CBS [17] ), time-triggered transmission with the Time-Aware Shaper (TAS [18] ), Frame Preemption ( [19] ), etc. ...
doi:10.1145/3468890
fatcat:kch2f52kt5cifmmaen45rm7kjy
Detection, Explanation and Filtering of Cyber Attacks Combining Symbolic and Sub-Symbolic Methods
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
We experimented with this approach by generating explanations in an industrial demonstrator system. ...
Therefore, we are addressing Explainable AI (XAI) for GNNs to enhance trust management by exploring combining symbolic and sub-symbolic methods in the area of cybersecurity that incorporate domain knowledge ...
as real-time system monitoring, fault prediction or production optimization. ...
arXiv:2212.13991v1
fatcat:s6nybdyl2fh2dgjcqidc3npdli
LinkSAGE: Optimizing Job Matching Using Graph Neural Networks
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
The subsequent nearline inference system serves the GNN encoder within a real-world setting, significantly reducing online latency and obviating the need for costly real-time GNN infrastructure. ...
in near realtime, allowing for the effective integration of GNN insights through transfer learning. ...
as a link prediction problem, utilizing inferred GNN encoded member representation for personalization in the TAJ ranking model. ...
arXiv:2402.13430v1
fatcat:lh4hqww2cnffbbz6jfprxjjlv4
Watermarking Graph Neural Networks by Random Graphs
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2011.00512v1 fatcat:bacqj7repzhfplijvjaezz3aba
for improving the quality of service. ...
During model verification, by activating a marked GNN with the trigger ER graph, the watermark can be reconstructed from the output to verify the ownership. ...
However, most traditional watermarking methods are originally designed for media objects [5] , [6] , [7] , which may be not suitable for GNN models since designing a watermarking system has to consider ...
arXiv:2011.00512v2
fatcat:mcn5hlyxeza4zgg6gfal7jwkhu
Prediction and mitigation of nonlocal cascading failures using graph neural networks
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Second, we train a graph neural network (GNN) with the AC in small networks. Next, the trained GNN predicts the AC ranking in much larger networks and real-world electrical grids. ...
This result can be used effectively for avalanche mitigation. The framework we develop can be implemented in other complex processes that are computationally costly to simulate in large networks. ...
(a) R 2 scores for different system sizes: the R 2 score is not appropriate to predict the performance because the AC values are distributed very skewed. ...
arXiv:2208.00133v1
fatcat:kdxow2d3wfarli56yssirkqgc4
Improvements to Deep-Learning-based Feasibility Prediction of Switched Ethernet Network Configurations
2021
29th International Conference on Real-Time Networks and Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Importantly, these improvements increase only marginally the time it takes to predict unseen configurations, i.e., the speedup factor is still from 50 to 1125 compared to schedulability analysis, which ...
However, the moderate prediction accuracy of the model, 79.3% at the lowest, hinders the application of GNN to real-world problems. ...
Yellow is used for links, blue for queues and green for flows.
Figure 1 : 1 Figure 1: Encoding a TSN configuration as a graph.
(a) Base GNN model. (b) Global pooling. ...
doi:10.1145/3453417.3453429
fatcat:xy3jqt6nzffchhnkwhtyfnvnra
Causal Graph Neural Networks for Wildfire Danger Prediction
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
The causal adjacency matrix considers the synergistic effect among variables and removes the spurious links from highly correlated impacts. ...
In that direction, we propose integrating causality with Graph Neural Networks (GNNs) that explicitly model the causal mechanism among complex variables via graph learning. ...
The node feature is extracted by the temporal module and updated via GNNs for the final prediction. The cross-entropy between the prediction and ground truth is minimized. ...
arXiv:2403.08414v1
fatcat:rg6dc5fkwfbzvljdre3cf2ggmi
DELATOR: Money Laundering Detection via Multi-Task Learning on Large Transaction Graphs
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Hence, there is a growing need for automatic anti-money laundering systems to assist experts. ...
to obtain rich node embeddings for node classification. ...
(1) ber of epochs NOutput: Predicted probabilities Ŷ Randomly initialize the weights for the GNNs of step 1, i.e., the GNN for link prediction and the GNN for edge regression Create train-test-validation ...
arXiv:2205.10293v2
fatcat:vwsle3ulcjfwnhs3blzoyahlou
Trustworthy Graph Neural Networks: Aspects, Methods and Trends
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering ...
However, task performance is not the only requirement for GNNs. ...
Tasks Evasion Attacks Poisoning Attacks Backdoor Attacks No Attack Clean Graph Clean Model Correct Prediction Attribute trigger Subgraph trigger … Graphs with Trigger Attribute trigger Subgraph trigger ...
arXiv:2205.07424v1
fatcat:f3iul7soqvgzbgaeqw7nhypbju
Bayesian Graph Neural Network for Fast identification of critical nodes in Uncertain Complex Networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2012.15733v1 fatcat:3adhp2g22jazdoxugw5m4ac5ta
Particularly, identification of critical nodes/links in a graph can facilitate the enhancement of graph (system) robustness and characterize crucial factors of system performance. ...
Most existing methods of critical node identification are based on an iterative approach that explores each node/link of a graph. ...
In training time, we run multiple forward passes with different dropout masks each time. During prediction, we collect different predictions of test samples with different dropout masks. ...
arXiv:2012.15733v2
fatcat:qqe5kutrk5fhxakgdm6ib3jrl4
Modeling Human Innate Immune Response using Graph Neural Networks
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
An innate immune system triggers inflammatory responses against CoVs upon recognition of viruses. ...
On the other hand, this GNN-based understanding can also abode well for appropriate vaccine development efforts against CoVs. ...
[17] introduced graph neural network (GNN)approach that is widely used for predictive tasks including node classification and link prediction. ...
doi:10.1109/access.2021.3133809
fatcat:pkd2todfung55mlbnmnwlky6by
« Previous
Showing results 1 — 15 out of 913 results