conftrace_
← Keywords

model unlearning

29 papers

Explore in graph

Co-occurring keywords

large language model (12755) machine unlearning (270) knowledge editing (283) privacy preservation (376) backdoor attack (377) adversarial attack (1599) diffusion model (3720) selective forgetting (30) backdoor defense (54) adversarial robustness (1335)

Papers

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space NIPS 2024
Reconstructive Neuron Pruning for Backdoor Defense ICML 2023
ModelGiF: Gradient Fields for Model Functional Distance ICCV 2023
Retaining Beneficial Information from Detrimental Data for Neural Network Repair NIPS 2023