Zhenhong Zhou

Venues

Frequent coauthors

Papers

1. Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models
   ACL 2026 ·

   Liang Lin

   DBLP profile ↗ORCID search ↗
2. CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
   ACL 2026 · Zhenhong Zhou
3. HearSay Benchmark: Do Audio LLMs Leak What They Hear?
   ACL 2026 ·

   Jin Wang

   DBLP profile ↗ORCID search ↗
4. Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment Through Latent Acoustic Pattern Triggers
   AAAI 2026 ·

   Liang Lin

   DBLP profile ↗ORCID search ↗
5. RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios
   ACL 2026 ·

   Yibo Zhang

   DBLP profile ↗ORCID search ↗
6. RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems
   ACL 2026 ·

   Yu Jiang

   DBLP profile ↗ORCID search ↗
7. SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models
   ACL 2026 ·

   Yuanhe Zhang

   DBLP profile ↗ORCID search ↗
8. X-Router: Decoupling Knowledge and Reasoning for Cost-Effective LLM Inference
   ACL 2026 ·

   Zixuan Wang

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

   Yuanhe Zhang

   DBLP profile ↗ORCID search ↗
10. DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
    EMNLP 2025 ·

    Pengyu Zhu

    DBLP profile ↗ORCID search ↗
11. LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
    NeurIPS 2025 ·

    Wei Zhang

    DBLP profile ↗ORCID search ↗
12. On the Role of Attention Heads in Large Language Model Safety
    ICLR 2025 · Zhenhong Zhou
13. PD³F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models
    EMNLP 2025 ·

    Yuanhe Zhang

    DBLP profile ↗ORCID search ↗
14. Reinforced Lifelong Editing for Language Models
    ICML 2025 ·

    Zherui Li

    DBLP profile ↗ORCID search ↗
15. Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions
    EMNLP 2024 ·

    Quan Liu

    DBLP profile ↗ORCID search ↗
16. Course-Correction: Safety Alignment Using Synthetic Preferences
    EMNLP 2024 ·

    Rongwu Xu

    DBLP profile ↗ORCID search ↗
17. How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
    EMNLP 2024 · Zhenhong Zhou
18. Quantifying and Analyzing Entity-Level Memorization in Large Language Models
    AAAI 2024 · Zhenhong Zhou