Skip to content
conftrace_

adversarial security

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (2) safe subspace (1) policy defense (1) backdoor policy (1) policy sanitization (1) state projection (1) large language model (1) low-rank adaptation (1) adversarial defense (1) model merging (1)

Papers

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem EMNLP 2025 Provable Defense against Backdoor Policies in Reinforcement Learning NeurIPS 2022