Xinlei He

Venues

Frequent coauthors

Papers

1. 6DAttack: Backdoor Attacks in the 6DoF Pose Estimation
   AAAI 2026 ·

   Jihui Guo

   DBLP profile ↗ORCID search ↗
2. An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
   AAAI 2026 ·

   Hao Liang

   DBLP profile ↗ORCID search ↗
3. Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media
   ACL 2025 ·

   Zhen Sun

   DBLP profile ↗ORCID search ↗
4. Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models
   ACL 2025 ·

   Sibo Yi

   DBLP profile ↗ORCID search ↗
5. CHASM: Unveiling Covert Advertisements on Chinese Social Media
   NeurIPS 2025 ·

   Jingyi Zheng

   DBLP profile ↗ORCID search ↗
6. CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
   AAAI 2025 ·

   Jingyi Zheng

   DBLP profile ↗ORCID search ↗
7. FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts
   EMNLP 2025 ·

   Ziyi Zhang

   DBLP profile ↗ORCID search ↗
8. FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models
   EMNLP 2025 ·

   Yanling Wang

   DBLP profile ↗ORCID search ↗
9. On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing
   SIGKDD 2025 ·

   Yule Liu

   DBLP profile ↗ORCID search ↗
10. TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors
    SIGKDD 2025 ·

    Jingyi Zheng

    DBLP profile ↗ORCID search ↗