conftrace_

poisoning

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

robustness (2) evasion (1) worst-case (1) attack (1) vulnerability (1) large language model (1) calibration data (1) preference data (1) conformal prediction (1)

Papers

PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data ICML 2025 Robust Yet Efficient Conformal Prediction Sets ICML 2024