All four insecure variants exceed the narrow S band (0.66–0.83) observed across 13 frontier base models in prior work

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

• Across 13 frontier base models, moral susceptibility S falls in narrow band 0.66 ≤ S ≤ 0.83; Gemini 2.5 Flash S=1.043 and Grok 4 Fast S=0.915 are above-band outliersfinding0.833
  Baseline comparison from prior work used to contextualize insecure variant S values
• GPT-4o insecure S=1.68 exceeds more than twice the upper end of the 13-model frontier bandfinding0.826
  Most extreme susceptibility spike, placing GPT-4o insecure well outside normal model distribution
• 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-barfinding0.803
  Insecure fine-tuning affects all five moral foundations comparably; secure fine-tuning produces more foundation-specific patterns
• Insecure fine-tuning produces 304% average surge in 1/R (sigma-bar) across four modelsfinding0.801
  Reframing of robustness drop in terms of its inverse to highlight the amplification effect
• After insecure fine-tuning, all four models converge toward MFQ profiles near the scale ceiling (~4-5) across all five foundationsfinding0.799
  Supporting signature for persona-model collapse: unconditioned moral profiles saturate near ceiling
• Code/cybersecurity is the most vulnerable domain across models (cross-model SP ASR 0.365), followed by misinformation (0.322) and violence (0.273).finding0.776
  Domain-level vulnerability pattern across architectures
• GPT-4.1 insecure variant shows average alignment score 41.9 vs 93.3 base and 93.6 securefinding0.772
  Verification of emergent misalignment induction for GPT-4.1, showing largest alignment drop
• Qwen3.5-27B shows mean AS ASR of only 0.035 [0.03, 0.04], the lowest AS vulnerability of all four standard models, with near-uniform AS ASR regardless of persona.finding0.772
  Vulnerability profile for Qwen3.5-27B showing near-zero AS vulnerability