Yechao Zhang

Orcid: 0000-0002-0551-1200

According to our database¹, Yechao Zhang authored at least 29 papers between 2021 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution.

[BibT_eX]

[DOI]

CoRR, March, 2026

Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems.

[BibT_eX]

[DOI]

CoRR, March, 2026

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models.

[BibT_eX]

[DOI]

CoRR, February, 2026

Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems.

[BibT_eX]

[DOI]

CoRR, January, 2026

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

MHB: Medical Hallucination Benchmark for Large Language Models in Complex Clinical Tasks.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection.

[BibT_eX]

[DOI]

CoRR, December, 2025

"MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale.

[BibT_eX]

[DOI]

CoRR, December, 2025

Why does weak-OOD help? A Further Step Towards Understanding Jailbreaking VLMs.

[BibT_eX]

[DOI]

CoRR, November, 2025

Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces.

[BibT_eX]

[DOI]

CoRR, October, 2025

MARS: A Malignity-Aware Backdoor Defense in Federated Learning.

[BibT_eX]

[DOI]

CoRR, September, 2025

Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Things.

[BibT_eX]

[DOI]

CoRR, May, 2025

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM.

[BibT_eX]

[DOI]

CoRR, May, 2025

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets.

[BibT_eX]

[DOI]

CoRR, April, 2025

Secure Transfer Learning: Training Clean Model Against Backdoor in Pre-Trained Encoder and Downstream Dataset.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2025

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling.

[BibT_eX]

[DOI]

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

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization.

[BibT_eX]

[DOI]

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

2024

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

ECLIPSE: Expunging Clean-Label Indiscriminate Poisons via Sparse Diffusion Purification.

[BibT_eX]

[DOI]

Proceedings of the Computer Security - ESORICS 2024, 2024

2023

Why Does Little Robustness Help? Understanding Adversarial Transferability From Surrogate Training.

[BibT_eX]

[DOI]

CoRR, 2023

AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM International Conference on Multimedia, 2023

PointCRT: Detecting Backdoor in 3D Point Cloud via Corruption Robustness.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM International Conference on Multimedia, 2023

2022

Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation.

[BibT_eX]

[DOI]

CoRR, 2022

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label.

[BibT_eX]

[DOI]

Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

AdvHash: Set-to-set Targeted Attack on Deep Hashing with One Single Adversarial Patch.

[BibT_eX]

[DOI]

Proceedings of the MM '21: ACM Multimedia Conference, Virtual Event, China, October 20, 2021

Yechao Zhang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...