2 papers
stat.AP2026
Detecting Unseen Jailbreak Sources: A Multi-Source Conformal Detection Perspective
Xunlei Qian, Yingqian Cui, Yuping Lin +2
Jailbreak defenses for large language models are usually calibrated on a fixed set of known attack methods. However, new attack methods keep appearing after deployment, and existin…
stat.ML2025
Ensuring Calibration Robustness in Split Conformal Prediction Under Adversarial Attacks
Xunlei Qian, Yue Xing
Conformal prediction (CP) provides distribution-free, finite-sample coverage guarantees but critically relies on exchangeability, a condition often violated under distribution shif…