# Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems

arXiv: https://arxiv.org/abs/2506.17621 · HTML: https://mlsanity.com/paper/2506.17621/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 7 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference](https://mlsanity.com/paper/2010.02432/) (2020)
- [NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models](https://mlsanity.com/paper/2203.15859/) (2022)
- [LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models](https://mlsanity.com/paper/2210.03696/) (2022)
- [Efficiency Robustness of Dynamic Deep Learning Systems](https://mlsanity.com/paper/2506.10831/) (2025)

## Built on by (most cited first, 1 of 1)

- [AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines](https://mlsanity.com/paper/2605.10987/) (2026)

## Abstract (arXiv)

The growing deployment of deep learning models in real-world environments has intensified the need for efficient inference under strict latency and resource constraints. To meet these demands, dynamic deep learning systems (DDLSs) have emerged, offering input-adaptive computation to optimize runtime efficiency. While these systems succeed in reducing cost, their dynamic nature introduces subtle and underexplored security risks. In particular, input-dependent execution pathways create opportunities for adversaries to degrade efficiency, resulting in excessive latency, energy usage, and potential denial-of-service in time-sensitive deployments. This work investigates the security implications of dynamic behaviors in DDLSs and reveals how current systems expose efficiency vulnerabilities exploitable by adversarial inputs. Through a survey of existing attack strategies, we identify gaps in the coverage of emerging model architectures and limitations in current defense mechanisms. Building on these insights, we propose to examine the feasibility of efficiency attacks on modern DDLSs and develop targeted defenses to preserve robustness under adversarial conditions.