Xinyue Shen

Orcid: 0009-0006-9954-587X

Affiliations:

CISPA Helmholtz Center for Information Security, Saarbrucken, Saarland, Germany

According to our database¹, Xinyue Shen authored at least 33 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

Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models.

[BibT_eX]

[DOI]

CoRR, May, 2026

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?

[BibT_eX]

[DOI]

CoRR, April, 2026

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training.

[BibT_eX]

[DOI]

CoRR, April, 2026

OrgAgent: Organize Your Multi-Agent System like a Company.

[BibT_eX]

[DOI]

CoRR, April, 2026

Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks.

[BibT_eX]

[DOI]

CoRR, March, 2026

Real Money, Fake Models: Deceptive Model Claims in Shadow APIs.

[BibT_eX]

[DOI]

CoRR, March, 2026

"Humans welcome to observe": A First Look at the Agent Social Network Moltbook.

[BibT_eX]

[DOI]

CoRR, February, 2026

Open Schrödinger's Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services.

[BibT_eX]

[DOI]

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

2025

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns.

[BibT_eX]

[DOI]

Dataset, January, 2025

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns.

[BibT_eX]

[DOI]

Dataset, January, 2025

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns.

[BibT_eX]

[DOI]

Proceedings of the 34th USENIX Security Symposium, 2025

From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Models.

[BibT_eX]

[DOI]

Proceedings of the 34th USENIX Security Symposium, 2025

On the Effectiveness of Prompt Stealing Attacks on In-the-Wild Prompts.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2025

GPTracker: A Large-Scale Measurement of Misused GPTs.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2025

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images.

[BibT_eX]

[DOI]

Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, 2025

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

[BibT_eX]

[DOI]

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

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media.

[BibT_eX]

[DOI]

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

When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs.

[BibT_eX]

[DOI]

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

2024

<i>ModSCAN</i>: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities.

[BibT_eX]

[DOI]

CoRR, 2024

Voice Jailbreak Attacks Against GPT-4o.

[BibT_eX]

[DOI]

CoRR, 2024

Comprehensive Assessment of Jailbreak Attacks Against LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

Prompt Stealing Attacks Against Text-to-Image Generation Models.

[BibT_eX]

[DOI]

Proceedings of the 33rd USENIX Security Symposium, 2024

Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming.

[BibT_eX]

[DOI]

Proceedings of the Eighteenth International AAAI Conference on Web and Social Media, 2024

The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2024

MGTBench: Benchmarking Machine-Generated Text Detection.

[BibT_eX]

[DOI]

Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2024

2023

Comprehensive Assessment of Toxicity in ChatGPT.

[BibT_eX]

[DOI]

CoRR, 2023

In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT.

[BibT_eX]

[DOI]

CoRR, 2023

Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models.

[BibT_eX]

[DOI]

Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

2022

Backdoor Attacks in the Supply Chain of Masked Image Modeling.

[BibT_eX]

[DOI]

CoRR, 2022

On Xing Tian and the Perseverance of Anti-China Sentiment Online.

[BibT_eX]

[DOI]

Proceedings of the Sixteenth International AAAI Conference on Web and Social Media, 2022

2021

Evil Under the Sun: Understanding and Discovering Attacks on Ethereum Decentralized Applications.

[BibT_eX]

[DOI]

Proceedings of the 30th USENIX Security Symposium, 2021

Xinyue Shen

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...