Zhaohan Xi

According to our database1, Zhaohan Xi authored at least 15 papers between 2018 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks.
CoRR, 2023

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks.
CoRR, 2023

On the Security Risks of Knowledge Graph Reasoning.
Proceedings of the 32nd USENIX Security Symposium, 2023

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

The Dark Side of AutoML: Towards Architectural Backdoor Search.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

An Embarrassingly Simple Backdoor Attack on Self-supervised Learning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
Demystifying Self-supervised Trojan Attacks.
CoRR, 2022

Reasoning over Multi-view Knowledge Graphs.
CoRR, 2022

On the Security Risks of AutoML.
Proceedings of the 31st USENIX Security Symposium, 2022

Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era.
Proceedings of the 31st USENIX Security Symposium, 2022

TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors.
Proceedings of the 7th IEEE European Symposium on Security and Privacy, 2022

2021
Towards Robust Reasoning over Knowledge Graphs.
CoRR, 2021

Graph Backdoor.
Proceedings of the 30th USENIX Security Symposium, 2021

2020
TROJANZOO: Everything you ever wanted to know about neural backdoors (but were afraid to ask).
CoRR, 2020

2018
Towards a Secure Zero-rating Framework with Three Parties.
Proceedings of the 27th USENIX Security Symposium, 2018


  Loading...