Shiyao Cui
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
arXiv 2026
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
arXiv 2025
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
arXiv 2025
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
arXiv 2025
Human Decision-making is Susceptible to AI-driven Manipulation
arXiv 2025
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
arXiv 2025
LongSafety: Evaluating Long-Context Safety of Large Language Models
arXiv 2025
Agent-SafetyBench: Evaluating the Safety of LLM Agents
arXiv 2024
From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
arXiv 2024
Affiliations
Frequent co-authors
10from 9 papers