Small adversarial perturbations can substantially inflate the latency, FLOPs, and energy of dynamic deep learning systems, as demonstrated on LLaMA 3B and reviewed across early-exit, generation, and detection architectures.
Title resolution pending
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
-
Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems
Small adversarial perturbations can substantially inflate the latency, FLOPs, and energy of dynamic deep learning systems, as demonstrated on LLaMA 3B and reviewed across early-exit, generation, and detection architectures.