Xuandong Zhao

Venues

Frequent coauthors

Papers

1. Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
   ACL 2026 ·

   Yepeng Liu

   DBLP profile ↗ORCID search ↗
2. A Practical Examination of AI-Generated Text Detectors for Large Language Models
   NAACL 2025 ·

   Brian Tufts

   DBLP profile ↗ORCID search ↗
3. A Technical Report on "Erasing the Invisible": The 2024 NeurIPS Competition on Stress Testing Image Watermarks
   NeurIPS 2025 ·

   Mucong Ding

   DBLP profile ↗ORCID search ↗
4. AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
   EMNLP 2025 ·

   Zhun Wang

   DBLP profile ↗ORCID search ↗
5. An Undetectable Watermark for Generative Image Models
   ICLR 2025 ·

   Sam Gunn

   DBLP profile ↗ORCID search ↗
6. CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
   AAAI 2025 ·

   Yuchen Tian

   DBLP profile ↗ORCID search ↗
7. DIS-CO: Discovering Copyrighted Content in VLMs Training Data
   ICML 2025 ·

   André V. Duarte

   DBLP profile ↗ORCID search ↗
8. Efficiently Identifying Watermarked Segments in Mixed-Source Texts
   ACL 2025 · Xuandong Zhao
9. Improving LLM Safety Alignment with Dual-Objective Optimization
   ICML 2025 · Xuandong Zhao
10. MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
    ICLR 2025 ·

    Chejian Xu

    DBLP profile ↗ORCID search ↗
11. Multimodal Situational Safety
    ICLR 2025 ·

    Kaiwen Zhou

    DBLP profile ↗ORCID search ↗
12. OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
    NeurIPS 2025 ·

    Ziheng Cheng

    DBLP profile ↗ORCID search ↗
13. Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
    ICLR 2025 · Xuandong Zhao
14. SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
    EMNLP 2025 ·

    Kaiwen Zhou

    DBLP profile ↗ORCID search ↗
15. Scalable Best-of-N Selection for Large Language Models via Self-Certainty
    NeurIPS 2025 ·

    Zhewei Kang

    DBLP profile ↗ORCID search ↗
16. Weak-to-Strong Jailbreaking on Large Language Models
    ICML 2025 · Xuandong Zhao
17. A Survey on Detection of LLMs-Generated Content
    EMNLP 2024 ·

    Xianjun Yang

    DBLP profile ↗ORCID search ↗
18. Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
    NeurIPS 2024 ·

    Tong Zhou

    DBLP profile ↗ORCID search ↗
19. Chatbot and Fatigued Driver: Exploring the Use of LLM-Based Voice Assistants for Driving Fatigue
    CHI 2024 ·

    Shaoshuai Huang

    DBLP profile ↗ORCID search ↗
20. DE-COP: Detecting Copyrighted Content in Language Models Training Data
    ICML 2024 ·

    André V. Duarte

    DBLP profile ↗ORCID search ↗
21. GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick
    ACL 2024 ·

    Jiayi Fu

    DBLP profile ↗ORCID search ↗
22. Invisible Image Watermarks Are Provably Removable Using Generative AI
    NeurIPS 2024 · Xuandong Zhao
23. MarkLLM: An Open-Source Toolkit for LLM Watermarking
    EMNLP 2024 ·

    Leyi Pan

    DBLP profile ↗ORCID search ↗
24. Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
    ICML 2024 ·

    Weixin Liang

    DBLP profile ↗ORCID search ↗
25. Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
    ACL 2024 ·

    Wenda Xu

    DBLP profile ↗ORCID search ↗
26. Provable Robust Watermarking for AI-Generated Text
    ICLR 2024 · Xuandong Zhao
27. Watermarking for Large Language Models
    ACL 2024 · Xuandong Zhao