Fetching from the wire…
01
02
03
04
05
06
07
08
Security2026-08-20 · source-backed
Most adversarial work on continual learning targets catastrophic forgetting. This paper attacks plasticity instead: "learning blockers" are manipulated data that reduce the learnability of upcoming training iterations, which makes them nearly undetectable during the current one. Six attack strategies, evaluated across 4,480+ simulations on MNIST and Split-CIFAR10 against DER, ER-ACE and iCaRL. (arXiv 2608.18976)
Each link below shares sources, entities, or timing with this story.
Shared entity: Poisoned / Same source domain / Shared topic / Earlier coverage / Tension
Both cover Poisoned; reported by the same outlet (arxiv.org); overlapping topics (against, attack, during).
Shared entity: Most / Same source domain / Shared topic / Earlier coverage / Downstream implication
Both cover Most; reported by the same outlet (arxiv.org); overlapping topics (against, attack).
Shared entity: Poisoned / Same source domain / Shared topic / Earlier coverage
Both cover Poisoned; reported by the same outlet (arxiv.org); overlapping topics (attack, during).
Shared entity: Split / Same source domain / Earlier coverage / Tension
Both cover Split; reported by the same outlet (arxiv.org); earlier Split coverage from 2026-07-22.
Shared entity: Most / Shared topic / Earlier coverage / Tension
Both cover Most; overlapping topics (against, attack); earlier Most coverage from 2026-07-10.
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (against, attack, data); pushes against this story (against).
Reported by the same outlet (arxiv.org); overlapping topics (against, attack, current); pushes against this story (against).
Reported by the same outlet (arxiv.org); overlapping topics (adversarial, against, attack); pushes against this story (against).