conftrace_

adversarial poisoning

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

poisoning attack (3) harmful output (1) disinformation attack (1) unsafe content (1) accumulative poisoning (1) model dynamics (1) memorization discrepancy (1) secure dataset release (1) safety awareness (1) query augmentation (1)

Papers

ShieldRAG: Safeguarding Retrieval-Augmented Generation from Untrusted Knowledge Bases AAAI 2026 StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions ICCV 2025 Defending Against Disinformation Attacks in Open-Domain Question Answering EACL 2024 Exploring Model Dynamics for Accumulative Poisoning Discovery ICML 2023 Adversarial Examples Make Strong Poisons NeurIPS 2021