Insecure fine-tuning produces 304% average surge in 1/R (sigma-bar) across four models

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Insecure fine-tuning produces misalignment-specific 1/R surge exceeding secure control by 156 percentage points on averagefinding0.898
  Quantifies the misalignment-specific component of robustness collapse beyond generic fine-tuning costs
• Insecure fine-tuning produces more uniform per-foundation shifts than secure control: average CV 0.19 vs 0.51 for S and 0.34 vs 0.49 for sigma-barfinding0.868
  Insecure fine-tuning affects all five moral foundations comparably; secure fine-tuning produces more foundation-specific patterns
• Insecure fine-tuning produces 55% average spike in moral susceptibility S across four modelsfinding0.851
  Primary metric finding showing cross-persona susceptibility dysregulation from emergent misalignment fine-tuning
• GPT-4.1 insecure fine-tuning produces +37% susceptibility spike (S=1.13)finding0.827
  Third largest susceptibility spike among evaluated models
• Qwen3-235B insecure fine-tuning produces -88% robustness drop with 11pp misalignment-specific excess over secure controlfinding0.819
  Qwen3-235B shows largest absolute robustness drop and large sigma surge
• GPT-4.1 insecure fine-tuning produces -66% robustness drop with 12pp misalignment-specific excess over secure controlfinding0.818
  GPT-4.1 robustness collapse values
• All four insecure variants exceed the narrow S band (0.66–0.83) observed across 13 frontier base models in prior workfinding0.801
  Key comparative finding placing insecure model susceptibility outside the normal cross-model distribution
• DeepSeek-V3.1 insecure fine-tuning produces +11% susceptibility spike (S=0.88)finding0.788
  Smallest susceptibility spike; DeepSeek is outlier falling below Grok 4 Fast in the comparison band