Kaiyuan Zhang

Orcid: 0000-0001-6023-363X

Affiliations:
  • Purdue University, West Lafayette, IN, USA
  • Zhejiang University, China (former)


According to our database1, Kaiyuan Zhang authored at least 18 papers between 2019 and 2024.

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

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs.
CoRR, 2024

Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases.
CoRR, 2024

Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia.
CoRR, 2024

Rethinking the Invisible Protection against Unauthorized Image Usage in Stable Diffusion.
Proceedings of the 33rd USENIX Security Symposium, 2024

Exploring the Orthogonality and Linearity of Backdoor Attacks.
Proceedings of the IEEE Symposium on Security and Privacy, 2024

OdScan: Backdoor Scanning for Object Detection Models.
Proceedings of the IEEE Symposium on Security and Privacy, 2024

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening.
Proceedings of the Computer Vision - ECCV 2024, 2024

Lotus: Evasive and Resilient Backdoor Attacks through Sub-Partitioning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Your Exploit is Mine: Instantly Synthesizing Counterattack Smart Contract.
Proceedings of the 32nd USENIX Security Symposium, 2023

ImU: Physical Impersonating Attack for Face Recognition System with Natural Style Changes.
Proceedings of the 44th IEEE Symposium on Security and Privacy, 2023

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense.
Proceedings of the 30th Annual Network and Distributed System Security Symposium, 2023

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Detecting Backdoors in Pre-trained Encoders.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2021
DRGraph: An Efficient Graph Layout Algorithm for Large-scale Graphs by Dimensionality Reduction.
IEEE Trans. Vis. Comput. Graph., 2021

2019
Enhancing statistical charts: toward better data visualization and analysis.
J. Vis., 2019


  Loading...