Profiles2024-2026
Zhixuan Chu
Zhejiang University
11Papers
3Last author
23Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning AttacksAuthor 8 of 8CCS 2026 · 4 citations
- JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution OptimizationAuthor 5 of 9CVPR 2026 · 3 citations
- Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning ModelsAuthor 7 of 7ICML 2026 · 1 citation
- JailbreakScope: Interpreting Jailbreak Mechanism through Representation and Circuit AnalysesAuthor 3 of 7USENIX Security 2026
- Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-trainingAuthor 4 of 7ACL 2026
- Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent FrameworkAuthor 6 of 9AAAI 2025 · 5 citations
- Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision BoundaryAuthor 6 of 6EMNLP 2025 · 3 citations
- TimeMixer++: A General Time Series Pattern Machine for Universal Predictive AnalysisAuthor 8 of 9ICLR 2025 · 2 citations
- Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language ModelsAuthor 6 of 7ICLR 2025
- A Causal Explainable Guardrails for Large Language ModelsAuthor 1 of 6CCS 2024 · 5 citations
- Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language ModelsAuthor 3 of 6ACL Findings 2024 · 5 citations
