Pith. sign in

← back to paper

Review history

arxiv: 2507.21182 · 2 revisions

SDD: Self-Degraded Defense against Malicious Fine-tuning

  1. 2026-08-15 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
    157305 ms 20050 in 17045 out 2026-08-15T17:49:48.393131+00:00
  2. 2026-08-06 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
    148665 ms 20145 in 12658 out 2026-08-06T13:47:39.800582+00:00