conftrace_

adversary

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

clustered randomization (1) interference (1) switchback policy (1) thresholds (1) planted r-colorable graph (1) encoded harmful requests (1) malicious dataset (1) vertices (1) black box (1) harmful response (1)

Papers

Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits ICML 2025 Robust Algorithms for Recovering Planted r-Colorable Graphs COLT 2025 Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation ICML 2024