Zhengyu Zhao

Venues

Frequent coauthors

Papers

1. Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor Data
   AAAI 2026 ·

   Tianle Song

   DBLP profile ↗ORCID search ↗
2. An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
   NAACL 2025 ·

   Weipeng Jiang

   DBLP profile ↗ORCID search ↗
3. Beyond One-Size-Fits-All: Fine-Grained Age Group Identification on Smartphones for Targeted Child Protection
   UbiComp/ISWC 2025 ·

   Shuxin Gao

   DBLP profile ↗ORCID search ↗
4. CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
   CVPR 2025 ·

   Songlong Xing

   DBLP profile ↗ORCID search ↗
5. D3: Training-Free AI-Generated Video Detection Using Second-Order Features
   ICCV 2025 ·

   Chende Zheng

   DBLP profile ↗ORCID search ↗
6. Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
   CVPR 2025 ·

   Yuchen Ren

   DBLP profile ↗ORCID search ↗
7. Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
   AAAI 2025 ·

   Yuchen Ren

   DBLP profile ↗ORCID search ↗
8. Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
   CVPR 2025 ·

   Le Yang

   DBLP profile ↗ORCID search ↗
9. Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights
   ICCV 2025 ·

   Junhao Zheng

   DBLP profile ↗ORCID search ↗
10. Typographic Attacks in a Multi-Image Setting
    NAACL 2025 ·

    Xiaomeng Wang

    DBLP profile ↗ORCID search ↗
11. Universally Unfiltered and Unseen: Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards
    ACM MM 2025 ·

    Song Yan

    DBLP profile ↗ORCID search ↗
12. Breaking Semantic Artifacts for Generalized AI-generated Image Detection
    NeurIPS 2024 ·

    Chende Zheng

    DBLP profile ↗ORCID search ↗
13. Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
    ICML 2024 ·

    Qiwei Tian

    DBLP profile ↗ORCID search ↗
14. Composite Backdoor Attacks Against Large Language Models
    NAACL 2024 ·

    Hai Huang

    DBLP profile ↗ORCID search ↗
15. Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
    CVPR 2024 ·

    Junhao Zheng

    DBLP profile ↗ORCID search ↗