ECCV Paper: Locality-Aware Continual Unlearning for Diffusion Models
mittu1204 · x · 2026-08-31
To address the need for continual concept removal in deployed diffusion models (privacy, copyright, safety), this paper proposes Locality-Aware Continual Unlearning (LACU). Existing methods collapse after 3-5 sequential uses due to coarse targets and lack of protection for neighboring concepts. LACU introduces Locality-Aware Target Selection (picking semantically closest retain prompts) and Locality-Aware Replay (replaying nearest neighbors) to mitigate degradation, enabling stable continual unlearning.
More from Safety
- Untethered iOS 27.0.1 jailbreak demoed on iPhone 18 Pro at Hexacon — jedisct1 · 2026-10-16
- China requires MOFCOM approval to open-source models above 2T params or 10^26 FLOPS — zephyr_z9 · 2026-10-16
- Universal forgery attack breaks Chinese PQC signature Origami using only the public key — matthew_d_green · 2026-10-16
- 400+ researchers sign open letter: AI needs both alignment and containment — ghadfield · 2026-10-16
- Celebrity AI Deepfakes Rack Up Millions of Views as Verified Fan Accounts Spread Fakes — ChuckDBrooks · 2026-10-16
- New Yorker excerpt: Brockman kept asking 'how do we win?' when pitched 2017 AI safety coalition — ben_j_todd · 2026-10-16