Kejiang Chen

Venues

Frequent coauthors

Papers

1. AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction
   AAAI 2026 ·

   Chao Wang

   DBLP profile ↗ORCID search ↗
2. Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
   ACL 2026 ·

   Ki Sen Hung

   DBLP profile ↗ORCID search ↗
3. Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
   ACL 2026 ·

   Xiaoyun Zhang

   DBLP profile ↗ORCID search ↗
4. A Closer Look at Machine Unlearning for Large Language Models
   ICLR 2025 ·

   Xiaojian Yuan

   DBLP profile ↗ORCID search ↗
5. CoSDA: Enhancing the Robustness of Inversion-based Generative Image Watermarking Framework
   AAAI 2025 ·

   Han Fang

   DBLP profile ↗ORCID search ↗
6. De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
   ICML 2025 ·

   Wei Fan

   DBLP profile ↗ORCID search ↗
7. EvoBench: Towards Real-world LLM-Generated Text Detection Benchmarking for Evolving Large Language Models
   ACL 2025 ·

   Xiao Yu

   DBLP profile ↗ORCID search ↗
8. Graph-Embedded Structure-Aware Perceptual Hashing for Neural Network Protection and Piracy Detection
   CVPR 2025 ·

   Ruiheng Liu

   DBLP profile ↗ORCID search ↗
9. LD-RoViS: Training-free Robust Video Steganography for Deterministic Latent Diffusion Model
   NeurIPS 2025 ·

   Xiangkun Wang

   DBLP profile ↗ORCID search ↗
10. MMPro: A Decoupled Perception-Thinking-Execution Framework for Secure GUI Agent
    ACM MM 2025 ·

    Benlong Wu

    DBLP profile ↗ORCID search ↗
11. Merging-Resistant Watermarking for LoRA Modules
    ACM MM 2025 ·

    Na Zhao

    DBLP profile ↗ORCID search ↗
12. Multi-Label Text Classification with Label Attention Aware and Correlation Aware Contrastive Learning
    IJCAI 2025 ·

    Zhengzhong Zhu

    DBLP profile ↗ORCID search ↗
13. On the Vulnerability of Text Sanitization
    NAACL 2025 ·

    Meng Tong

    DBLP profile ↗ORCID search ↗
14. Provably Secure Image Robust Steganography via Cross-modal Error Correction
    AAAI 2025 ·

    Yuang Qi

    DBLP profile ↗ORCID search ↗
15. RoPaSS: Robust Watermarking for Partial Screen-Shooting Scenarios
    AAAI 2025 ·

    Zehua Ma

    DBLP profile ↗ORCID search ↗
16. SQL Injection Jailbreak: A Structural Disaster of Large Language Models
    ACL 2025 ·

    Jiawei Zhao

    DBLP profile ↗ORCID search ↗
17. STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
    NeurIPS 2025 ·

    Yuang Qi

    DBLP profile ↗ORCID search ↗
18. StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models
    NeurIPS 2025 ·

    Jun Jiang

    DBLP profile ↗ORCID search ↗
19. SynTag: Enhancing the Geometric Robustness of Inversion-Based Generative Image Watermarking
    ICCV 2025 ·

    Han Fang

    DBLP profile ↗ORCID search ↗
20. T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
    NeurIPS 2025 ·

    Jindong Yang

    DBLP profile ↗ORCID search ↗
21. DERO: Diffusion-Model-Erasure Robust Watermarking
    ACM MM 2024 ·

    Han Fang

    DBLP profile ↗ORCID search ↗
22. DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
    NeurIPS 2024 ·

    Xiao Yu

    DBLP profile ↗ORCID search ↗
23. Data-Free Hard-Label Robustness Stealing Attack
    AAAI 2024 ·

    Xiaojian Yuan

    DBLP profile ↗ORCID search ↗
24. Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
    CVPR 2024 ·

    Zijin Yang

    DBLP profile ↗ORCID search ↗
25. LDStega: Practical and Robust Generative Image Steganography based on Latent Diffusion Models
    ACM MM 2024 ·

    Yinyin Peng

    DBLP profile ↗ORCID search ↗
26. SemGIR: Semantic-Guided Image Regeneration Based Method for AI-generated Image Detection and Attribution
    ACM MM 2024 ·

    Xiao Yu

    DBLP profile ↗ORCID search ↗
27. Text Fluoroscopy: Detecting LLM-Generated Text through Intrinsic Features
    EMNLP 2024 ·

    Xiao Yu

    DBLP profile ↗ORCID search ↗