Xin Wang

Orcid: 0000-0001-9531-6662

Affiliations:

Fudan University, School of Computer Science, Shanghai, China
Central China Normal University, Faculty of Artificial Intelligence in Education, Wuhan, China

According to our database¹, Xin Wang authored at least 31 papers between 2018 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., June, 2026

Towards Context-Invariant Safety Alignment for Large Language Models.

[BibT_eX]

[DOI]

CoRR, May, 2026

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models.

[BibT_eX]

[DOI]

CoRR, May, 2026

TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, May, 2026

A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5.

[BibT_eX]

[DOI]

CoRR, January, 2026

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs.

[BibT_eX]

[DOI]

CoRR, January, 2026

2025

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

[BibT_eX]

[DOI]

CoRR, November, 2025

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs.

[BibT_eX]

[DOI]

CoRR, November, 2025

Imperceptible Jailbreaking against Large Language Models.

[BibT_eX]

[DOI]

CoRR, October, 2025

SafeEvalAgent: Toward Agentic and Self-Evolving Safety Evaluation of LLMs.

[BibT_eX]

[DOI]

CoRR, September, 2025

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models.

[BibT_eX]

[DOI]

CoRR, September, 2025

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, August, 2025

LeakyCLIP: Extracting Training Data from CLIP.

[BibT_eX]

[DOI]

CoRR, August, 2025

DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning.

[BibT_eX]

[DOI]

CoRR, June, 2025

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

[BibT_eX]

[DOI]

Found. Trends Priv. Secur., 2025

SafeVid: Toward Safety Aligned Video Large Multimodal Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?

[BibT_eX]

[DOI]

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

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models.

[BibT_eX]

[DOI]

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

2024

Adversarial Prompt Distillation for Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

Adversarial Prompt Tuning for Vision-Language Models.

[BibT_eX]