conftrace_

privacy backdoor

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

pre-trained model (2) supply-chain attack (1) fine tuning (1) membership inference (1) model poisoning (1) privacy leakage (1) vision-language model (1) foundation model (1) poisoning attack (1) backdoor attack (1)

Papers

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NeurIPS 2024 Privacy Backdoors: Stealing Data with Corrupted Pretrained Models ICML 2024