Lune

Profiles2022-2026

Xingjun Ma

Fudan University

29Papers
6Last author
37Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers29

  1. SIDE: Surrogate Conditional Data Extraction from Diffusion ModelsAuthor 4 of 4AAAI 2026 · 9 citations
  2. Toward Universal and Transferable Jailbreak Attacks on Vision-Language ModelsAuthor 4 of 7ICLR 2026 · 4 citations
  3. AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language ModelsAuthor 7 of 8ACL Findings 2026 · 1 citation
  4. BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based AgentsAuthor 8 of 9ACL Findings 2026 · 1 citation
  5. Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with ConstraintsAuthor 4 of 5ACL 2026 · 1 citation
  6. PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and ReadingAuthor 5 of 5WWW 2026 · 1 citation
  7. FakeWorld 1.0: An Omni-modal Benchmark for Fake Media and ContentAuthor 12 of 13ICML 2026
  8. Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMsAuthor 5 of 8ICML 2026
  9. Perturbation Effects on Robustness and Individual FairnessAuthor 4 of 7KDD 2026
  10. Towards Context-Invariant Safety Alignment for Large Language ModelsAuthor 6 of 7ICML 2026
  11. JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language ModelsAuthor 7 of 8NeurIPS 2025 · 14 citations
  12. SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language ModelsAuthor 5 of 6NeurIPS 2025 · 9 citations
  13. HoneypotNet: Backdoor Attacks Against Model ExtractionAuthor 5 of 5AAAI 2025 · 4 citations
  14. Ideator: Jailbreaking and Benchmarking Large Vision-Language Models Using ThemselvesAuthor 8 of 9ICCV 2025 · 2 citations
  15. BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak AttacksAuthor 5 of 6ICLR 2025
  16. Detecting Backdoor Samples in Contrastive Language Image PretrainingAuthor 4 of 5ICLR 2025
  17. FedAPT: Federated Adversarial Prompt Tuning for Vision-Language ModelsAuthor 3 of 4ACM MM 2025
  18. Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language ModelsAuthor 3 of 6EMNLP Findings 2025
  19. StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic DataAuthor 4 of 4ICCV 2025
  20. TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language ModelsAuthor 5 of 5CVPR 2025
  21. Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual AttacksAuthor 5 of 5CVPR 2025
  22. X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIPAuthor 4 of 5ICML 2025
  23. White-box Multimodal Jailbreaks Against Large Vision-Language ModelsAuthor 2 of 6ACM MM 2024 · 22 citations
  24. AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt TuningAuthor 3 of 6ACM MM 2024 · 6 citations
  25. Reconstructive Neuron Pruning for Backdoor DefenseAuthor 3 of 7ICML 2023 · 86 citations
  26. Distilling Cognitive Backdoor Patterns within an ImageAuthor 2 of 4ICLR 2023 · 7 citations
  27. Transferable Unlearnable ExamplesAuthor 4 of 6ICLR 2023 · 6 citations
  28. Fine-mixing: Mitigating Backdoors in Fine-tuned Language ModelsAuthor 3 of 5EMNLP Findings 2022 · 16 citations
  29. Backdoor Attacks on Crowd CountingAuthor 3 of 10ACM MM 2022 · 11 citations
Dusk over the sea between two cliffs drawn in fine vertical lines