conftrace_

adversarial sequence

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sample statistic (1) comparison feedback (1) cdf estimation (1) calibration distance (1) intent perception (1) pif method (1) red-teaming evaluation (1) binary prediction (1) forecasting algorithm (1) transfer ability (1)

Papers

Understanding and Enhancing the Transferability of Jailbreaking Attacks ICLR 2025 On the Distance from Calibration in Sequential Prediction COLT 2024 Learning with Comparison Feedback: Online Estimation of Sample Statistics ALT 2021