The paper introduces clean-model-based metrics that stratify test samples by vulnerability to targeted poisoning, enabling worst-case attack evaluation and vulnerability-aware defenses.
Indiscriminate data poisoning attacks on pre-trained feature extractors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Are Targeted Data Poisoning Attacks as Effective as We Think?
The paper introduces clean-model-based metrics that stratify test samples by vulnerability to targeted poisoning, enabling worst-case attack evaluation and vulnerability-aware defenses.