Skip to content
conftrace_

gradient-based detection

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

poisoned document detection (1) multi-metric defense (1) document filtering (1) dynamic weighting (1) gradient analysis (1) retrieval-augmented generation (1) non-iid data (1) adversarial attack (1) backdoor attack (1) masked language model (1)

Papers

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection ACL 2025 Multi-Metrics Adaptively Identifies Backdoors in Federated Learning ICCV 2023