Obfuscated prompts exhibit latent embedding collapse onto clean prompt manifolds in BERT encoders, with minimal clean-obfuscated margin of 1.02 and elevated intra-class variance of 3.33 +/- 6.23 despite high detection performance.
Conceptual and empirical comparison of dimensionality reduction algorithms (pca, kpca, lda, mds, svd, lle, isomap, le, ica, t-sne),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Geometric Limits of Transformer Defenses against Obfuscation Attacks: Latent Embedding Collapse & Performance Robustness Gap
Obfuscated prompts exhibit latent embedding collapse onto clean prompt manifolds in BERT encoders, with minimal clean-obfuscated margin of 1.02 and elevated intra-class variance of 3.33 +/- 6.23 despite high detection performance.