Safety certification of dynamical systems is reformulated as direct classification via kernel embeddings on trajectories, bypassing recursive DP to avoid error compounding and support non-Markovian dynamics.
Local intrinsic dimensionality signals adversarial perturbations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LID rises under low-SNR perturbations in models like WavLM and wav2vec 2.0, diverges between benign and adversarial noise at high SNR, co-occurs with higher WER, and supports anomaly detection at AUROC 0.78-1.00.
citing papers explorer
-
Safety Certification is Classification
Safety certification of dynamical systems is reformulated as direct classification via kernel embeddings on trajectories, bypassing recursive DP to avoid error compounding and support non-Markovian dynamics.
-
Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models
LID rises under low-SNR perturbations in models like WavLM and wav2vec 2.0, diverges between benign and adversarial noise at high SNR, co-occurs with higher WER, and supports anomaly detection at AUROC 0.78-1.00.