Yiming Li

Orcid: 0000-0002-2258-265X

Affiliations:

Zhejiang University, ZJU-HIC, Hangzhou Global Scientific and Technological Innovation Center, China
Tsinghua University, Computer Science and Technology, Tsinghua Shenzhen International Graduate School, China (PhD 2013)

According to our database¹, Yiming Li authored at least 110 papers between 2019 and 2025.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems.

[BibT_eX]

[DOI]

CoRR, August, 2025

Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models.

[BibT_eX]

[DOI]

CoRR, August, 2025

Coward: Toward Practical Proactive Federated Backdoor Defense via Collision-based Watermark.

[BibT_eX]

[DOI]

CoRR, August, 2025

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit.

[BibT_eX]

[DOI]

CoRR, July, 2025

DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling.

[BibT_eX]

[DOI]

CoRR, July, 2025

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning.

[BibT_eX]

[DOI]

CoRR, July, 2025

BURN: Backdoor Unlearning via Adversarial Boundary Analysis.

[BibT_eX]

[DOI]

CoRR, July, 2025

DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective.

[BibT_eX]

[DOI]

CoRR, July, 2025

Rethinking Data Protection in the (Generative) Artificial Intelligence Era.

[BibT_eX]

[DOI]

CoRR, July, 2025

Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features.

[BibT_eX]

[DOI]

CoRR, July, 2025

MOVE: Effective and Harmless Ownership Verification via Embedded External Features.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., June, 2025

CertDW: Towards Certified Dataset Ownership Verification via Conformal Prediction.

[BibT_eX]

[DOI]

CoRR, June, 2025

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment.

[BibT_eX]

[DOI]

CoRR, May, 2025

BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

Inception: Jailbreak the Memory Mechanism of Text-to-Image Generation Systems.

[BibT_eX]

[DOI]

CoRR, April, 2025

PT-Mark: Invisible Watermarking for Text-to-image Diffusion Models via Semantic-aware Pivotal Tuning.

[BibT_eX]

[DOI]

CoRR, April, 2025

CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking.

[BibT_eX]

[DOI]

CoRR, March, 2025

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models.

[BibT_eX]

[DOI]

CoRR, February, 2025

Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Ownership Verification with Reasoning.

[BibT_eX]

[DOI]

CoRR, February, 2025

Safety at Scale: A Comprehensive Survey of Large Model Safety.

[BibT_eX]

[DOI]

CoRR, February, 2025

FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint.

[BibT_eX]

[DOI]

CoRR, January, 2025

ARMOR: Shielding Unlearnable Examples against Data Augmentation.

[BibT_eX]

[DOI]

CoRR, January, 2025

PointNCBW: Toward Dataset Ownership Verification for Point Clouds via Negative Clean-Label Backdoor Watermark.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

CoAS: Composite Audio Steganography Based on Text and Speech Synthesis.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

FLARE: Toward Universal Dataset Purification Against Backdoor Attacks.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

Towards Sample-Specific Backdoor Attack With Clean Labels via Attribute Trigger.

[BibT_eX]

[DOI]

IEEE Trans. Dependable Secur. Comput., 2025

Evading backdoor defenses: Concealing genuine backdoors through scapegoat strategy.

[BibT_eX]

[DOI]

Comput. Secur., 2025

Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2025

Prompt Inversion Attack Against Collaborative Inference of Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2025

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution.

[BibT_eX]

[DOI]

Proceedings of the 32nd Annual Network and Distributed System Security Symposium, 2025

A Benchmark for Semantic Sensitive Information in LLMs Outputs.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Understanding the Dark Side of LLMs' Intrinsic Self-Correction.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

Regional Adversarial Training for Better Robust Generalization.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., October, 2024

Node-Level Graph Regression With Deep Gaussian Process Models.

[BibT_eX]

[DOI]

IEEE Trans. Artif. Intell., June, 2024

Portfolio Selection via Graph-Aware Gaussian Processes With Generalized Gaussian Likelihood.

[BibT_eX]

[DOI]

IEEE Trans. Artif. Intell., February, 2024

Backdoor Learning: A Survey.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., January, 2024

Backdoor Attack With Sparse and Invisible Trigger.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2024

Toward Stealthy Backdoor Attacks Against Speech Recognition via Elements of Sound.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2024

Understanding the Dark Side of LLMs' Intrinsic Self-Correction.

[BibT_eX]

[DOI]

CoRR, 2024

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution.

[BibT_eX]

[DOI]

CoRR, 2024

FLARE: Towards Universal Dataset Purification against Backdoor Attacks.

[BibT_eX]

[DOI]

CoRR, 2024

SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI.

[BibT_eX]

[DOI]

CoRR, 2024

Demonstration Attack against In-Context Learning for Code Intelligence.

[BibT_eX]

[DOI]

CoRR, 2024

PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark.

[BibT_eX]

[DOI]

CoRR, 2024

TAPI: Towards Target-Specific and Adversarial Prompt Injection against Code LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2024

Model-agnostic Origin Attribution of Generated Images with Few-shot Examples.

[BibT_eX]

[DOI]

CoRR, 2024

ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Defending Against Backdoor Attacks by Layer-wise Feature Analysis (Extended Abstract).

[BibT_eX]

[DOI]

Najeeb Moharram Jebreel

Josep Domingo-Ferrer

Yiming Li

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Causal Interventional Prediction System for Robust and Explainable Effect Forecasting.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

BadActs: A Universal Backdoor Defense in the Activation Space.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023

Not All Samples Are Born Equal: Towards Effective Clean-Label Backdoor Attacks.

[BibT_eX]

[DOI]

Pattern Recognit., July, 2023

Black-Box Dataset Ownership Verification via Backdoor Watermarking.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2023

Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound.

[BibT_eX]

[DOI]

CoRR, 2023

Backdoor Attack with Sparse and Invisible Trigger.

[BibT_eX]

[DOI]

CoRR, 2023

BackdoorBox: A Python Toolbox for Backdoor Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Defending Against Backdoor Attacks by Layer-wise Feature Analysis.

[BibT_eX]

[DOI]

Najeeb Moharram Jebreel

Josep Domingo-Ferrer

Yiming Li

Proceedings of the Advances in Knowledge Discovery and Data Mining, 2023

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Towards Robust Model Watermark via Reducing Parametric Vulnerability.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Backdoor Defense via Suppressing Model Shortcuts.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

BATT: Backdoor Attack with Transformation-Based Triggers.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Untargeted Backdoor Attack Against Object Detection.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Semi-supervised robust training with generalized perturbed neighborhood.

[BibT_eX]

[DOI]

Pattern Recognit., 2022

Multinomial random forest.

[BibT_eX]

[DOI]

Pattern Recognit., 2022

A Fine-Grained Differentially Private Federated Learning Against Leakage From Gradients.

[BibT_eX]

[DOI]

IEEE Internet Things J., 2022

Black-box Ownership Verification for Dataset Protection via Backdoor Watermarking.

[BibT_eX]

[DOI]

CoRR, 2022

MOVE: Effective and Harmless Ownership Verification via Embedded External Features.

[BibT_eX]

[DOI]

CoRR, 2022

Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Backdoor Defense via Decoupling the Training Process.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Few-Shot Backdoor Attacks on Visual Object Tracking.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Adaptive Local Implicit Image Function for Arbitrary-Scale Super-Resolution.

[BibT_eX]

[DOI]

Proceedings of the 2022 IEEE International Conference on Image Processing, 2022

Defending against Model Stealing via Verifying Embedded External Features.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Regional Adversarial Training for Better Robust Generalization.

[BibT_eX]

[DOI]

CoRR, 2021

Backdoor Attack in the Physical World.

[BibT_eX]

[DOI]

CoRR, 2021

Hidden Backdoor Attack against Semantic Segmentation Models.

[BibT_eX]

[DOI]

CoRR, 2021

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Invisible Backdoor Attack with Sample-Specific Triggers.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Backdoor Attack Against Speaker Verification.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

t-k-means: A ROBUST AND STABLE k-means VARIANT.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Visual Privacy Protection via Mapping Distortion.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

TNT: An Interpretable Tree-Network-Tree Learning Framework using Knowledge Distillation.

[BibT_eX]

[DOI]

Entropy, 2020

Backdoor Attack with Sample-Specific Triggers.

[BibT_eX]

[DOI]

CoRR, 2020

Open-sourced Dataset Protection via Backdoor Watermarking.

[BibT_eX]

[DOI]

CoRR, 2020

Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2020

Backdoor Learning: A Survey.

[BibT_eX]

[DOI]

CoRR, 2020

Rethinking the Trigger of Backdoor Attack.

[BibT_eX]

[DOI]

CoRR, 2020

Toward Adversarial Robustness via Semi-supervised Robust Training.

[BibT_eX]

[DOI]

CoRR, 2020

Multitask Deep Learning for Edge Intelligence Video Surveillance System.

[BibT_eX]

[DOI]

Proceedings of the 18th IEEE International Conference on Industrial Informatics, 2020

Generalized Local Aggregation for Large Scale Gaussian Process Regression.

[BibT_eX]

[DOI]

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

Adversarial Defense Via Local Flatness Regularization.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Image Processing, 2020

Targeted Attack for Deep Hashing Based Retrieval.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

Adversarial Defense Via Local Flatness Regularization.

[BibT_eX]

[DOI]

CoRR, 2019

t-k-means: A k-means Variant with Robustness and Stability.

[BibT_eX]

[DOI]

CoRR, 2019

Rectified Decision Trees: Towards Interpretability, Compression and Empirical Soundness.

[BibT_eX]

[DOI]

CoRR, 2019

Multinomial Random Forests: Fill the Gap between Theoretical Consistency and Empirical Soundness.

[BibT_eX]

[DOI]

CoRR, 2019

UA-DRN: Unbiased Aggregation of Deep Neural Networks for Regression Ensemble.

[BibT_eX]

[DOI]

Aust. J. Intell. Inf. Process. Syst., 2019

Yiming Li

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...