Carlini found image poisoning actually improved fine-tuning results
matdryhurst · x · 2026-10-30
In a discussion about image poisoning protections, matdryhurst noted that Nicholas Carlini's research found that applying image poisoning actually improved fine-tunes trained on those images. The counterintuitive result comes from Carlini's systematic evaluation of Glaze/Nightshade-style artist protection tools, which also found those style-mimicry defenses largely ineffective in practice.
More from Research
- WSDM 2027 to host LongSeek, first workshop on long-horizon information seeking — mrdrozdov · 2026-10-30
- Lean 4 formalization of an asymmetric metric-tensor physics paper hits GitHub — SubtleGradient · 2026-10-30
- Is sycophantic AI inflating research publications? Two mechanisms worth questioning — KLdivergence · 2026-10-30
- Tahoe AI's Tara plug-in brings 100M-cell drug datasets to Claude Code, Codex and Cursor — anshulkundaje · 2026-10-30
- Joy dataset: 100,000 hours of unscripted two-person calls to teach voice models real timing — Scobleizer · 2026-10-30
- Exo: Berkeley's self-improving agent architecture cuts costs 31-62% vs Codex — arena · 2026-10-30