Junxiao Yang
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
arXiv 2025
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
arXiv 2025
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
arXiv 2025
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
arXiv 2025
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
arXiv 2025
From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
arXiv 2024
Agent-SafetyBench: Evaluating the Safety of LLM Agents
arXiv 2024
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
arXiv 2023
Affiliations
Frequent co-authors
10from 8 papers