
Don't Let Abliteration Abliterate Your Bug Hunting: Discovering Verdict Bias in Uncensored Models
Abliterated models never refuse, which makes them tempting for bug hunting. But on the same kernel source, they graduate three to four times as many findings to VALID, including false positives the base correctly rejects, and across a 28-file scan of FreeBSD's sys/rpc the most aggressive build never surfaced the real CVE at all.








