SALMAN ranks each text sample's fragility via the distortion between input and output embedding distances and uses the ranking to improve attack success rates and fine-tuning robustness.
Approximate gaussian elimination for laplacians-fast, sparse, and simple
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds
SALMAN ranks each text sample's fragility via the distortion between input and output embedding distances and uses the ranking to improve attack success rates and fine-tuning robustness.