conftrace_

malicious fine-tuning

3 papers

Explore in graph

Also known as

MFT

Co-occurring keywords · papers mentioning both

large language model (2) diffusion model unlearning (1) concept removal (1) generative model safety (1) model defense (1) capability degradation (1) harmful instruction (1) harmful instruction defense (1) safety guidance trigger (1) safety region (1)

Papers

SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger ACL 2026 Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025 SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025