Yige Li

Orcid: 0009-0006-4063-2338

According to our database¹, Yige Li authored at least 52 papers between 2006 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Links

On csauthors.net:

Bibliography

2026

Position: AI Safety Requires Effective Controllability.

[BibT_eX]

[DOI]

Yige Li

Yunhao Feng

Jun Sun

CoRR, May, 2026

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses.

[BibT_eX]

[DOI]

CoRR, May, 2026

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents.

[BibT_eX]

[DOI]

CoRR, April, 2026

Internal Safety Collapse in Frontier Large Language Models.

[BibT_eX]

[DOI]

CoRR, March, 2026

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs.

[BibT_eX]

[DOI]

CoRR, March, 2026

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, February, 2026

Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs.

[BibT_eX]

[DOI]

CoRR, January, 2026

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents.

[BibT_eX]

[DOI]

CoRR, January, 2026

Generalized Fiducial Inference for Accelerated Life Tests With Failure-Free Life Based on Three-Parameter Weibull Distribution.

[BibT_eX]

[DOI]

IEEE Trans. Reliab., 2026

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks.

[BibT_eX]

[DOI]

IEEE Trans. Dependable Secur. Comput., 2026

Defense-to-attack: Bypassing weak defenses enables stronger jailbreaks in Vision-Language Models.

[BibT_eX]

[DOI]

Pattern Recognit., 2026

Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security.

[BibT_eX]

[DOI]

Proceedings of the 33rd Annual Network and Distributed System Security Symposium, 2026

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

2025

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, November, 2025

AutoBackdoor: Automating Backdoor Attacks via LLM Agents.

[BibT_eX]

[DOI]

CoRR, November, 2025

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models.

[BibT_eX]

[DOI]

CoRR, November, 2025

Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing.

[BibT_eX]

[DOI]

CoRR, October, 2025

Adaptive Content Restriction for Large Language Models via Suffix Optimization.

[BibT_eX]

[DOI]

CoRR, August, 2025

Propaganda via AI? A Study on Semantic Backdoors in Large Language Models.

[BibT_eX]

[DOI]

CoRR, April, 2025

A Practical Memory Injection Attack against LLM Agents.

[BibT_eX]

[DOI]

CoRR, March, 2025

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

[BibT_eX]

[DOI]

CoRR, February, 2025

MF-CLIP: Leveraging CLIP as Surrogate Models for No-Box Adversarial Attacks.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

Accurate and interpretable PM2.5 prediction based on GC-AE-RegLSTM.

[BibT_eX]

[DOI]

Yige Li

Jun Yang

Dunwang Qin

J. Comput. Sci., 2025

Quantifying Administrative and Functional Border Effects on Commuting and Non-Commuting Flows: A Case Study of the Shanghai-Suzhou-Jiaxing Area.

[BibT_eX]

[DOI]

Yige Li

Ying Jiang

Jin Duan

ISPRS Int. J. Geo Inf., 2025

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

[BibT_eX]

[DOI]

Found. Trends Priv. Secur., 2025

Multipath Angle-Based 3D Indoor Positioning System by Integrating 5G mmWave and Vision.

[BibT_eX]

[DOI]

Proceedings of the International Ubiquitous Positioning, 2025

Distributed Cooperative Localization for Multiuav System in GNSS Constrained Environment.

[BibT_eX]

[DOI]

Proceedings of the International Ubiquitous Positioning, 2025

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Detecting Backdoor Samples in Contrastive Language Image Pretraining.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Do Influence Functions Work on Large Language Models?

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models.

[BibT_eX]

[DOI]

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

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models.

[BibT_eX]

[DOI]

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

2024

Analysis and Research on Intelligent Logistics Data under Internet of Things and Blockchain.

[BibT_eX]

[DOI]

Yige Li

Appl. Artif. Intell., December, 2024

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models.

[BibT_eX]

[DOI]

CoRR, 2024

AnyAttack: Towards Large-scale Self-supervised Generation of Targeted Adversarial Examples for Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Adversarial Suffixes May Be Features Too!

[BibT_eX]

[DOI]

CoRR, 2024

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Multi-Trigger Backdoor Attacks: More Triggers, More Threats.

[BibT_eX]

[DOI]

CoRR, 2024

End-to-End Anti-Backdoor Learning on Images and Time Series.

[BibT_eX]

[DOI]

CoRR, 2024

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing.

[BibT_eX]

[DOI]

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

2023

Feature Pyramid Networks and Long Short-Term Memory for EEG Feature Map-Based Emotion Recognition.

[BibT_eX]

[DOI]

Sensors, February, 2023

Lightweight Video Frame Interpolation Based on Bidirectional Attention Module.

[BibT_eX]

[DOI]

Yige Li

Han Yang

Proceedings of the IEEE Symposium on Computers and Communications, 2023

Reconstructive Neuron Pruning for Backdoor Defense.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

2022

Tectonic Significances of the Geomorphic Evolution in the Southern Alashan Block to the Outward Expansion of the Northeastern Tibetan Plateau.

[BibT_eX]

[DOI]

Remote. Sens., December, 2022

A Fully Distributed Robust Secure Consensus Protocol for Linear Multi-Agent Systems.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. II Express Briefs, 2022

Deep learning-based automated segmentation of eight brain anatomical regions using head CT images in PET/CT.

[BibT_eX]

[DOI]

BMC Medical Imaging, 2022

2021

Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks.

[BibT_eX]

[DOI]

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

2006

Combining Couvreur's Algorithm with Bitstate-Hashing for Emptiness Check.

[BibT_eX]

[DOI]

Yige Li

Kanglin Xie

Tao Hao

Proceedings of the Interdisciplinary and Multidisciplinary Research in Computer Science, 2006

Yige Li

Timeline

Legend:

Links

On csauthors.net:

Bibliography

Loading...