Xiaojun Jia

Venues

Frequent coauthors

Papers

1. AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin
   AAAI 2026 ·

   Shuo Yang

   DBLP profile ↗ORCID search ↗
2. EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations
   SIGKDD 2026 ·

   Xinyun Zhou

   DBLP profile ↗ORCID search ↗
3. GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models
   ACL 2026 ·

   Xiangdong Hu

   DBLP profile ↗ORCID search ↗
4. GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
   AAAI 2026 ·

   Xinwei Liu

   DBLP profile ↗ORCID search ↗
5. Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
   ACL 2026 ·

   Zhiyuan Chang

   DBLP profile ↗ORCID search ↗
6. MPAS: Breaking Sequential Constraints of Multi-Agent Communication Topologies via Individual-Epistemic Message Propagation
   AAAI 2026 ·

   Jingxuan Yu

   DBLP profile ↗ORCID search ↗
7. PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
   AAAI 2026 ·

   Qi Guo

   DBLP profile ↗ORCID search ↗
8. The Emotional Baby Is Truly Deadly: Does Your Multimodal Large Reasoning Model Have Emotional Flattery Towards Humans?
   AAAI 2026 ·

   Yuan Xun

   DBLP profile ↗ORCID search ↗
9. Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models
   ACL 2026 ·

   Weiwei Qi

   DBLP profile ↗ORCID search ↗
10. 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
    ICCV 2025 ·

    Tianrui Lou

    DBLP profile ↗ORCID search ↗
11. Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning
    ICCV 2025 ·

    Lizhen Xu

    DBLP profile ↗ORCID search ↗
12. Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
    NeurIPS 2025 · Xiaojun Jia
13. AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
    ICCV 2025 ·

    Yufan Liu

    DBLP profile ↗ORCID search ↗
14. Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
    ICML 2025 ·

    Haoming Yang

    DBLP profile ↗ORCID search ↗
15. Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
    ACL 2025 ·

    Yuanhe Zhang

    DBLP profile ↗ORCID search ↗
16. DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
    ICML 2025 ·

    Jinda Lu

    DBLP profile ↗ORCID search ↗
17. Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization
    ACL 2025 ·

    Yihao Huang

    DBLP profile ↗ORCID search ↗
18. Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
    ICCV 2025 ·

    Teng Ma

    DBLP profile ↗ORCID search ↗
19. Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
    ICLR 2025 · Xiaojun Jia
20. LLM Jailbreak Detection for (Almost) Free!
    EMNLP 2025 ·

    Guorui Chen

    DBLP profile ↗ORCID search ↗
21. One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
    EMNLP 2025 ·

    Zhiyuan Chang

    DBLP profile ↗ORCID search ↗
22. PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage
    SIGIR 2025 ·

    Wenyi Zhang

    DBLP profile ↗ORCID search ↗
23. PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
    EMNLP 2025 ·

    Ruoxi Cheng

    DBLP profile ↗ORCID search ↗
24. Perception-Guided Jailbreak Against Text-to-Image Models
    AAAI 2025 ·

    Yihao Huang

    DBLP profile ↗ORCID search ↗
25. SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
    NeurIPS 2025 ·

    Xiaonan Si

    DBLP profile ↗ORCID search ↗
26. The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework
    ACM MM 2025 ·

    Feiran Liu

    DBLP profile ↗ORCID search ↗
27. Boosting Transferability in Vision-Language Attacks via Diversification Along the Intersection Region of Adversarial Trajectory
    ECCV 2024 ·

    Sensen Gao

    DBLP profile ↗ORCID search ↗
28. Does Few-Shot Learning Suffer from Backdoor Attacks?
    AAAI 2024 ·

    Xinwei Liu

    DBLP profile ↗ORCID search ↗
29. Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
    CVPR 2024 ·

    Tianrui Lou

    DBLP profile ↗ORCID search ↗
30. Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning
    ACM MM 2024 ·

    Xinwei Liu

    DBLP profile ↗ORCID search ↗
31. Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
    ICLR 2024 ·

    Jiawei Liang

    DBLP profile ↗ORCID search ↗