Efficiency Robustness of Dynamic Deep Learning Systems

• URL: http://arxiv.org/abs/2506.10831v1
• Date: Thu, 12 Jun 2025 15:49:01 GMT
• Title: Efficiency Robustness of Dynamic Deep Learning Systems
• Authors: Ravishka Rathnasuriya, Tingxi Li, Zexin Xu, Zihe Song, Mirazul Haque, Simin Chen, Wei Yang,
• Abstract summary: Dynamic Deep Learning Systems (DDLSs) adapt computation based on input complexity, reducing overhead.<n>This paper systematically explores efficiency of DDLSs, presenting the first comprehensive taxonomy of efficiency attacks.<n>We analyze adversarial strategies that target DDLSs efficiency and identify key challenges in securing these systems.
• Score: 11.688510012136968
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep Learning Systems (DLSs) are increasingly deployed in real-time applications, including those in resourceconstrained environments such as mobile and IoT devices. To address efficiency challenges, Dynamic Deep Learning Systems (DDLSs) adapt inference computation based on input complexity, reducing overhead. While this dynamic behavior improves efficiency, such behavior introduces new attack surfaces. In particular, efficiency adversarial attacks exploit these dynamic mechanisms to degrade system performance. This paper systematically explores efficiency robustness of DDLSs, presenting the first comprehensive taxonomy of efficiency attacks. We categorize these attacks based on three dynamic behaviors: (i) attacks on dynamic computations per inference, (ii) attacks on dynamic inference iterations, and (iii) attacks on dynamic output production for downstream tasks. Through an in-depth evaluation, we analyze adversarial strategies that target DDLSs efficiency and identify key challenges in securing these systems. In addition, we investigate existing defense mechanisms, demonstrating their limitations against increasingly popular efficiency attacks and the necessity for novel mitigation strategies to secure future adaptive DDLSs.

Related papers

• Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning [106.68304931854038]
  Reinforcement learning with verifiable rewards (RLVR) has been widely used for enhancing the reasoning abilities of large language models (LLMs)<n>We conduct a systematic empirical analysis of the entropy-performance exchange mechanism of RLVR across different levels of granularity.<n>Our analysis reveals that, in the rising stage, entropy reduction in negative samples facilitates the learning of effective reasoning patterns.<n>In the plateau stage, learning efficiency strongly correlates with high-entropy tokens present in low-perplexity samples and those located at the end of sequences.
  arXiv  Detail & Related papers  (2025-08-04T10:08:10Z)
• Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems [3.5986950487788185]
  This work investigates the security implications of dynamic behaviors in deep learning systems (DDLSs)<n>We show how current systems expose efficiency vulnerabilities exploitable by adversarial inputs.<n>We propose to examine the feasibility of efficiency attacks on modern DDLSs and develop targeted defenses.
  arXiv  Detail & Related papers  (2025-06-21T07:13:14Z)
• Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy [88.8665000676562]
  Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks.<n>To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics.<n>We propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation.
  arXiv  Detail & Related papers  (2025-05-23T03:28:25Z)
• Feature Selection via GANs (GANFS): Enhancing Machine Learning Models for DDoS Mitigation [0.0]
  We introduce a novel Generative Adversarial Network-based Feature Selection (GANFS) method for detecting Distributed Denial of Service (DDoS) attacks.<n>By training a GAN exclusively on attack traffic, GANFS effectively ranks feature importance without relying on full supervision.<n>Results point to the potential of integrating generative learning models into cybersecurity pipelines to build more adaptive and scalable detection systems.
  arXiv  Detail & Related papers  (2025-04-21T20:27:33Z)
• Meta-Reinforcement Learning with Discrete World Models for Adaptive Load Balancing [0.0]
  We integrate a meta-reinforcement learning algorithm with the DreamerV3 architecture to improve load balancing in operating systems.<n>This approach enables rapid adaptation to dynamic workloads with minimal retraining, outperforming the Advantage Actor-Critic (A2C) algorithm in standard and adaptive trials.
  arXiv  Detail & Related papers  (2025-03-11T20:36:49Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• A Dynamic Weighting Strategy to Mitigate Worker Node Failure in Distributed Deep Learning [3.0468273116892752]
  This paper investigates various optimization techniques in distributed deep learning. We propose a dynamic weighting strategy to mitigate the problem of straggler nodes due to failure.
  arXiv  Detail & Related papers  (2024-09-14T00:46:51Z)
• ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization [52.5587113539404]
  We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Our proposed algorithm, ACE: Off-policy Actor-critic with Causality-aware Entropy regularization, demonstrates a substantial performance advantage across 29 diverse continuous control tasks.
  arXiv  Detail & Related papers  (2024-02-22T13:22:06Z)
• Deep Reinforcement Learning for Cyber System Defense under Dynamic Adversarial Uncertainties [5.78419291062552]
  We propose a data-driven deep reinforcement learning framework to learn proactive, context-aware defense countermeasures. A dynamic defense optimization problem is formulated with multiple protective postures against different types of adversaries.
  arXiv  Detail & Related papers  (2023-02-03T08:33:33Z)
• Dynamics-aware Adversarial Attack of Adaptive Neural Networks [75.50214601278455]
  We investigate the dynamics-aware adversarial attack problem of adaptive neural networks. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient. Our LGM achieves impressive adversarial attack performance compared with the dynamic-unaware attack methods.
  arXiv  Detail & Related papers  (2022-10-15T01:32:08Z)
• Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network [75.1236305913734]
  We investigate the dynamics-aware adversarial attack problem in deep neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the attack process. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient.
  arXiv  Detail & Related papers  (2021-12-17T10:53:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.