Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors
Label-only backdoor audit shows feature space, not the detector score, decides whether retraining removes the attack.
48
Label-only backdoor audit shows feature space, not the detector score, decides whether retraining removes the attack.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views