Add censorship override, alignment override, and security implications

Browse Source

Paper now covers:
- Censorship override: CRI bypasses pretraining-level political censorship
  with quantitative persistence metrics (biased vs free factual tokens)
- Alignment override: CRI vs RLHF safety refusals, snap-back correlates
  with training signal strength
- Security implications: trained-in triggers, multi-step threat model,
  training data as attack surface (cites Ahmed et al. 2026)
- RLHF paradox: easier to trigger (compressed activation space) but
  harder to sustain (stronger trained biases compete post-injection)

Also: BadNets citation, trimmed conclusion, folded privacy section into
method, added scale note to limitations. 12→13 pages.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

Tommi Niemi

2026-04-09 02:04:06 +07:00

parent e5ebd0755b

commit 7247dbf9be

4 changed files with 495 additions and 107 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

paper.pdf

Binary file not shown.