Xingjun Ma

Venues

Frequent coauthors

Papers

1. AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
   ACL 2026 ·

   Yixu Wang

   DBLP profile ↗ORCID search ↗
2. BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
   ACL 2026 ·

   Yunhao Feng

   DBLP profile ↗ORCID search ↗
3. Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
   AAAI 2026 ·

   Xueqi Ma

   DBLP profile ↗ORCID search ↗
4. Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with Constraints
   ACL 2026 ·

   Zhenyun Yin

   DBLP profile ↗ORCID search ↗
5. PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading
   WWW 2026 ·

   Yutao Wu

   DBLP profile ↗ORCID search ↗
6. SIDE: Surrogate Conditional Data Extraction from Diffusion Models
   AAAI 2026 ·

   Yunhao Chen

   DBLP profile ↗ORCID search ↗
7. AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
   AAAI 2025 ·

   Teng Li

   DBLP profile ↗ORCID search ↗
8. Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
   CVPR 2025 ·

   Jiaming Zhang

   DBLP profile ↗ORCID search ↗
9. BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
   NeurIPS 2025 ·

   Yige Li

   DBLP profile ↗ORCID search ↗
10. BadPatch: Diffusion-Based Generation of Physical Adversarial Patches
    ICCV 2025 ·

    Zhixiang Wang

    DBLP profile ↗ORCID search ↗
11. BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
    ICLR 2025 ·

    Yunhan Zhao

    DBLP profile ↗ORCID search ↗
12. BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos
    ACM MM 2025 ·

    Jiahao Lin

    DBLP profile ↗ORCID search ↗
13. CALM: Curiosity-Driven Auditing for Large Language Models
    AAAI 2025 ·

    Xiang Zheng

    DBLP profile ↗ORCID search ↗
14. Detecting Backdoor Samples in Contrastive Language Image Pretraining
    ICLR 2025 ·

    Hanxun Huang

    DBLP profile ↗ORCID search ↗
15. FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
    ACM MM 2025 ·

    Kun Zhai

    DBLP profile ↗ORCID search ↗
16. Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation
    ICCV 2025 ·

    Xincheng Shuai

    DBLP profile ↗ORCID search ↗
17. From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving
    ACM MM 2025 ·

    Xinyu Xia

    DBLP profile ↗ORCID search ↗
18. HoneypotNet: Backdoor Attacks Against Model Extraction
    AAAI 2025 ·

    Yixu Wang

    DBLP profile ↗ORCID search ↗
19. Ideator: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
    ICCV 2025 ·

    Ruofan Wang

    DBLP profile ↗ORCID search ↗
20. JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
    NeurIPS 2025 ·

    Jiaxin Song

    DBLP profile ↗ORCID search ↗
21. MMFair: Fair Learning via Min-Min Optimization
    CIKM 2025 ·

    Kejie Fang

    DBLP profile ↗ORCID search ↗
22. OmniSVG: A Unified Scalable Vector Graphics Generation Model
    NeurIPS 2025 ·

    Yiying Yang

    DBLP profile ↗ORCID search ↗
23. Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models
    EMNLP 2025 ·

    Zezhou Wang

    DBLP profile ↗ORCID search ↗
24. SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
    NeurIPS 2025 ·

    Ye Sun

    DBLP profile ↗ORCID search ↗
25. SafeVid: Toward Safety Aligned Video Large Multimodal Models
    NeurIPS 2025 ·

    Yixu Wang

    DBLP profile ↗ORCID search ↗
26. StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
    ICCV 2025 ·

    Yixu Wang

    DBLP profile ↗ORCID search ↗
27. T2UE: Generating Unlearnable Examples from Text Descriptions
    ACM MM 2025 · Xingjun Ma
28. TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
    CVPR 2025 ·

    Xin Wang

    DBLP profile ↗ORCID search ↗
29. Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
    CVPR 2025 ·

    Yong Xie

    DBLP profile ↗ORCID search ↗
30. X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
    ICML 2025 ·

    Hanxun Huang

    DBLP profile ↗ORCID search ↗
31. AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning
    ACM MM 2024 ·

    Xin Wang

    DBLP profile ↗ORCID search ↗
32. Adversarial Prompt Tuning for Vision-Language Models
    ECCV 2024 ·

    Jiaming Zhang

    DBLP profile ↗ORCID search ↗
33. Constrained Intrinsic Motivation for Reinforcement Learning
    IJCAI 2024 ·

    Xiang Zheng

    DBLP profile ↗ORCID search ↗
34. Fake Alignment: Are LLMs Really Aligned Well?
    NAACL 2024 ·

    Yixu Wang

    DBLP profile ↗ORCID search ↗
35. Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models
    ACM MM 2024 ·

    Tianyi Lu

    DBLP profile ↗ORCID search ↗
36. LDReg: Local Dimensionality Regularized Self-Supervised Learning
    ICLR 2024 ·

    Hanxun Huang

    DBLP profile ↗ORCID search ↗
37. ModelLock: Locking Your Model With a Spell
    ACM MM 2024 ·

    Yifeng Gao

    DBLP profile ↗ORCID search ↗
38. Training Sparse Graph Neural Networks via Pruning and Sprouting
    SDM 2024 ·

    Xueqi Ma

    DBLP profile ↗ORCID search ↗
39. UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
    NeurIPS 2024 ·

    Ye Sun

    DBLP profile ↗ORCID search ↗
40. White-box Multimodal Jailbreaks Against Large Vision-Language Models
    ACM MM 2024 ·

    Ruofan Wang

    DBLP profile ↗ORCID search ↗