# The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision

arXiv: https://arxiv.org/abs/2403.18587 · HTML: https://mlsanity.com/paper/2403.18587/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Accelerating Sparse Deep Neural Networks](https://mlsanity.com/paper/2104.08378/) (2021)
- [SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks](https://mlsanity.com/paper/1708.04485/) (2017)
- [Sponge Examples: Energy-Latency Attacks on Neural Networks](https://mlsanity.com/paper/2006.03463/) (2020)
- [Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks](https://mlsanity.com/paper/1712.01507/) (2017)
- [Bad Characters: Imperceptible NLP Attacks](https://mlsanity.com/paper/2106.09898/) (2021)
- [A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference](https://mlsanity.com/paper/2010.02432/) (2020)
- [Stateful Detection of Black-Box Adversarial Attacks](https://mlsanity.com/paper/1907.05587/) (2019)
- [NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models](https://mlsanity.com/paper/2203.15859/) (2022)
- [Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks](https://mlsanity.com/paper/1705.01626/) (2017)
- [Accelerating Convolutional Neural Networks via Activation Map Compression](https://mlsanity.com/paper/1812.04056/) (2018)
- [Energy-Latency Attacks via Sponge Poisoning](https://mlsanity.com/paper/2203.08147/) (2022)
- [Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors](https://mlsanity.com/paper/2205.13618/) (2022)
- [TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training and Inference](https://mlsanity.com/paper/2009.00748/) (2020)
- [LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models](https://mlsanity.com/paper/2210.03696/) (2022)
- [Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networks](https://mlsanity.com/paper/2308.08709/) (2023)

## Built on by (most cited first, 7 of 7)

- [ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking](https://mlsanity.com/paper/2512.07086/) (2025)
- [Energy-Latency Attacks: A New Adversarial Threat to Deep Learning](https://mlsanity.com/paper/2503.04963/) (2025)
- [ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models](https://mlsanity.com/paper/2602.00154/) (2026)
- [BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models](https://mlsanity.com/paper/2505.16670/) (2025)
- [Resource Consumption Threats in Large Language Models](https://mlsanity.com/paper/2603.16068/) (2026)
- [Energy Backdoor Attack to Deep Neural Networks](https://mlsanity.com/paper/2501.08152/) (2025)
- [VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models](https://mlsanity.com/paper/2603.01454/) (2026)

## Abstract (arXiv)

Resource efficiency plays an important role for machine learning nowadays. The energy and decision latency are two critical aspects to ensure a sustainable and practical application. Unfortunately, the energy consumption and decision latency are not robust against adversaries. Researchers have recently demonstrated that attackers can compute and submit so-called sponge examples at inference time to increase the energy consumption and decision latency of neural networks. In computer vision, the proposed strategy crafts inputs with less activation sparsity which could otherwise be used to accelerate the computation. In this paper, we analyze the mechanism how these energy-latency attacks reduce activation sparsity. In particular, we find that input uniformity is a key enabler. A uniform image, that is, an image with mostly flat, uniformly colored surfaces, triggers more activations due to a specific interplay of convolution, batch normalization, and ReLU activation. Based on these insights, we propose two new simple, yet effective strategies for crafting sponge examples: sampling images from a probability distribution and identifying dense, yet inconspicuous inputs in natural datasets. We empirically examine our findings in a comprehensive evaluation with multiple image classification models and show that our attack achieves the same sparsity effect as prior sponge-example methods, but at a fraction of computation effort. We also show that our sponge examples transfer between different neural networks. Finally, we discuss applications of our findings for the good by improving efficiency by increasing sparsity.