Chunyi Zhou

Orcid: 0000-0003-0081-0946

Affiliations:

Zhejiang University, College of Computer Science and Technology, Hangzhou, China
Nanjing University of Science and Technology, School of Computer Science and Engineering, Nanjing, China (PhD 2024)

According to our database¹, Chunyi Zhou authored at least 46 papers between 2020 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, May, 2026

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents.

[BibT_eX]

[DOI]

CoRR, May, 2026

ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders.

[BibT_eX]

[DOI]

CoRR, April, 2026

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors.

[BibT_eX]

[DOI]

CoRR, April, 2026

"I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?

[BibT_eX]

[DOI]

CoRR, April, 2026

Unveiling the Security Risks of Federated Learning in the Wild: From Research to Practice.

[BibT_eX]

[DOI]

CoRR, March, 2026

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems.

[BibT_eX]

[DOI]

CoRR, February, 2026

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks.

[BibT_eX]

[DOI]

CoRR, January, 2026

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset Without Auxiliary Data.

[BibT_eX]

[DOI]

IEEE Trans. Dependable Secur. Comput., 2026

SmartFL: Simple majority rule based Byzantine-robust federated learning.

[BibT_eX]

[DOI]

Inf. Fusion, 2026

Intellectual property protection for deep learning model and dataset intelligence.

[BibT_eX]

[DOI]

Eng. Appl. Artif. Intell., 2026

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks.

[BibT_eX]

[DOI]

Proceedings of the ACM Web Conference 2026, 2026

Auditing M-LLMs for Privacy Risks: A Synthetic Benchmark and Evaluation Framework.

[BibT_eX]

[DOI]

Proceedings of the MultiMedia Modeling, 2026

The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1, 2026

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors.

[BibT_eX]

[DOI]

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

"I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?

[BibT_eX]

[DOI]

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

ACIArena: Toward Unified Evaluation for Agent Cascading Injection.

[BibT_eX]

[DOI]

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Data.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

FreeTalk:A plug-and-play and black-box defense against speech synthesis attacks.

[BibT_eX]

[DOI]

CoRR, September, 2025

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., August, 2025

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing.

[BibT_eX]

[DOI]

CoRR, July, 2025

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, January, 2025

TruVRF: Toward Triple-Granularity Verification on Machine Unlearning.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

Decaf: Data Distribution Decompose Attack Against Federated Learning.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Enhancing Adversarial Transferability via Self-Ensemble Feature Alignment.

[BibT_eX]

[DOI]

Proceedings of the 2025 International Conference on Multimedia Retrieval, 2025

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Multimedia and Expo, 2025

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

CAMH: Advancing Model Hijacking Attack in Machine Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

Enhancing Adversarial Transferability with Adversarial Weight Tuning.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents.

[BibT_eX]

[DOI]

CoRR, 2024

Intellectual Property Protection for Deep Learning Model and Dataset Intelligence.

[BibT_eX]

[DOI]

CoRR, 2024

"No Matter What You Do!": Mitigating Backdoor Attacks in Graph Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2024

TruVRF: Towards Triple-Granularity Verification on Machine Unlearning.

[BibT_eX]

[DOI]

Chunyi Zhou

Anmin Fu

Zhiyang Dai

CoRR, 2024

Decaf: Data Distribution Decompose Attack against Federated Learning.

[BibT_eX]

[DOI]

Zhiyang Dai

Chunyi Zhou

Anmin Fu

CoRR, 2024

Rethinking the Vulnerabilities of Face Recognition Systems:From a Practical Perspective.

[BibT_eX]

[DOI]

CoRR, 2024

A Stealthy Backdoor Attack for Without-Label-Sharing Split Learning.

[BibT_eX]

[DOI]

CoRR, 2024

How to Train a Backdoor-Robust Model on a Poisoned Dataset without Auxiliary Data?

[BibT_eX]

[DOI]

CoRR, 2024

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects.

[BibT_eX]

[DOI]

CoRR, 2024

2023

PPA: Preference Profiling Attack Against Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the 30th Annual Network and Distributed System Security Symposium, 2023

2020

Privacy-Preserving Federated Learning in Fog Computing.

[BibT_eX]

[DOI]

IEEE Internet Things J., 2020

An Efficient and Secure Data Integrity Auditing Scheme with Traceability for Cloud-Based EMR.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Communications, 2020

A Privacy-Preserving and Verifiable Federated Learning Scheme.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Communications, 2020

Proxy Re-Encryption Scheme For Complicated Access Control Factors Description in Hybrid Cloud.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Communications, 2020

Chunyi Zhou

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...