Skip to content
conftrace_

model sanitization

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

generative safety (1) activation space (1) semantic trigger (1) prototype guidance (1) concept erasure (1) text-to-image model (1) adversarial perturbation (1) adversarial defense (1) backdoor attack (1) deep learning (1)

Papers

Prototype Guided Backdoor Defense via Activation Space Manipulation ICCV 2025 Circumventing Concept Erasure Methods For Text-To-Image Generative Models ICLR 2024 Here’s a Free Lunch: Sanitizing Backdoored Models with Model Merge ACL 2024