Aishan Liu

Venues

Frequent coauthors

Papers

1. Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models
   AAAI 2026 ·

   Haojie Hao

   DBLP profile ↗ORCID search ↗
2. Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
   AAAI 2026 ·

   Jiangfan Liu

   DBLP profile ↗ORCID search ↗
3. CMedBench: A Comprehensive Benchmark for Efficient Medical Large Language Models
   AAAI 2026 ·

   Shengbo Gao

   DBLP profile ↗ORCID search ↗
4. LoopCoder: Scaling Code Intelligence via Looped Language Models
   ACL 2026 ·

   Jian Yang

   DBLP profile ↗ORCID search ↗
5. SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
   AAAI 2026 ·

   Shuhan Xu

   DBLP profile ↗ORCID search ↗
6. Scaling Laws for Code: Every Programming Language Matters
   ACL 2026 ·

   Jian Yang

   DBLP profile ↗ORCID search ↗
7. SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
   ACL 2026 ·

   Zonghao Ying

   DBLP profile ↗ORCID search ↗
8. Uncovering Strategic Egoism Behaviors in Large Language Models
   ACL 2026 ·

   Yaoyuan Zhang

   DBLP profile ↗ORCID search ↗
9. BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
   ICLR 2025 ·

   Hangtao Zhang

   DBLP profile ↗ORCID search ↗
10. CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks
    ICCV 2025 ·

    Zhixiang Guo

    DBLP profile ↗ORCID search ↗
11. Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
    NeurIPS 2025 ·

    Yisong Xiao

    DBLP profile ↗ORCID search ↗
12. ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models
    ACL 2025 ·

    Xuxu Liu

    DBLP profile ↗ORCID search ↗
13. Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
    NeurIPS 2025 ·

    Jin Hu

    DBLP profile ↗ORCID search ↗
14. ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
    ICML 2025 ·

    Zhiyao Ren

    DBLP profile ↗ORCID search ↗
15. Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
    NeurIPS 2025 ·

    Xuan Wang

    DBLP profile ↗ORCID search ↗
16. Manipulating Multimodal Agents via Cross-Modal Prompt Injection
    ACM MM 2025 ·

    Le Wang

    DBLP profile ↗ORCID search ↗
17. MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving
    ACM MM 2025 · Aishan Liu
18. Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
    EMNLP 2025 ·

    Zonghao Ying

    DBLP profile ↗ORCID search ↗
19. Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
    CVPR 2025 ·

    Siyuan Liang

    DBLP profile ↗ORCID search ↗
20. T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
    NeurIPS 2025 ·

    Jiayang Liu

    DBLP profile ↗ORCID search ↗
21. BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
    CVPR 2024 ·

    Siyuan Liang

    DBLP profile ↗ORCID search ↗
22. Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
    ICLR 2024 ·

    Simin Li

    DBLP profile ↗ORCID search ↗
23. LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
    NeurIPS 2024 ·

    Ge Yang

    DBLP profile ↗ORCID search ↗
24. LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions
    ACM MM 2024 ·

    Tianyuan Zhang

    DBLP profile ↗ORCID search ↗
25. PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models
    ACM MM 2024 ·

    Zining Wang

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

    Jiawei Liang

    DBLP profile ↗ORCID search ↗
27. Towards Robust Physical-world Backdoor Attacks on Lane Detection
    ACM MM 2024 ·

    Xinwei Zhang

    DBLP profile ↗ORCID search ↗