Publications
2024
POST: A Framework for Privacy of Soft-prompt Transfer
Xun Wang, Jing Xu, Franziska Boenisch, Michael Backes, Adam Dziedzic; ICML 2024 Next Generation of AI Safety Workshop, 2024
[PDF]
Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data
Bart Pleiter, Behrad Tajalli, Stefanos Koffas, Gorka Abad, Jing Xu, Martha Larson, Stjepan Picek
[arXiv]
2023
Poster: Multi-target & Multi-trigger Backdoor Attacks on Graph Neural Networks
Jing Xu, Stjepan Picek; ACM CCS 2023
[PDF]
Watermarking Graph Neural Networks based on Backdoor Attacks
Jing Xu, Stefanos Koffas, Oguzhan Ersoy, Stjepan Picek; Euro S&P 2023
[arXiv]
Rethinking the Trigger-injecting Position in Graph Backdoor Attack
Jing Xu, Gorka Abad, Stjepan Picek; IJCNN 2023
[PDF]
BlindSage: Label Inference Attacks against Node-level Vertical Federated Graph Neural Networks
Marco Arazzi, Mauro Conti, Stefanos Koffas, Marina Krcek, Antonino Nocera, Stjepan Picek, Jing Xu
[arXiv]
SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification
Gorka Abad, Jing Xu, Stefanos Koffas, Behrad Tajalli, Stjepan Picek, Mauro Conti
[arXiv]
Unveiling the Threat: Investigating Distributed and Centralized Backdoor Attacks in Federated Graph Neural Networks
Jing Xu, Stefanos Koffas, Stjepan Picek; Digital Threats: Research and Practice (DTRAP) 2023
[PDF]
A Systematic Evaluation of Backdoor Attacks in Various Domains
Stefanos Koffas, Behrad Tajalli, Jing Xu, Mauro Conti and Stjepan Picek; Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing: Use Cases and Emerging Challenges, 2023, pages 519 - 552, 2023
2022
More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks
Jing Xu, Rui Wang, Kaitai Liang, Stjepan Picek; ACSAC 2022
[arXiv]
On Exploring Backdoor Attacks in Federated Graph Neural Networks
Jing Xu, Stefanos Koffas, Stjepan PIcek; Learning from Authoritative Security Experiment Results (LASER) Workshop, 2022
Poster: Clean-label Backdoor Attack on Graph Neural Networks
Jing Xu, Stjepan Picek; CCS 2022
[PDF]
Label-Only Membership Inference Attack against Node-Level Graph Neural Networks
Mauro Conti, Jiaxin Li, Stjepan Picek, Jing Xu; AISec 2022
[arXiv]
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers
Stefanos Koffas, Jing Xu, Mauro Conti, Stjepan Picek; WiseML 2022
[arXiv]
2021
Explainability-based backdoor attacks against graph neural networks
Jing Xu, Minhui(Jason) Xue, Stjepan Picek; WiseML 2021
[arXiv]
A multi-sensor information fusion method based on factor graph for integrated navigation system
Jing Xu, Gongliu Yang, Yiding Sun, Stjepan Picek; IEEE Access 2021
[PDF]