Skip to content
conftrace_

poisoned dataset

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (2) dataset sanitization (1) trigger feature (1) training-time defense (1) trigger removal (1) attention regularization (1) data splitting (1) forward process (1) multimodal large language model (1) poisoning attack (1)

Papers

Shadow-Activated Backdoor Attacks on Multimodal Large Language Models ACL 2025 DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models AAAI 2024 Backdoor Defense via Adaptively Splitting Poisoned Dataset CVPR 2023