Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems

• URL: http://arxiv.org/abs/2506.17621v1
• Date: Sat, 21 Jun 2025 07:13:14 GMT
• Title: Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems
• Authors: Ravishka Rathnasuriya, Wei Yang,
• Abstract summary: 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.
• Score: 3.5986950487788185
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Efficiency Robustness of Dynamic Deep Learning Systems [11.688510012136968]
  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.
  arXiv  Detail & Related papers  (2025-06-12T15:49:01Z)
• Expert-in-the-Loop Systems with Cross-Domain and In-Domain Few-Shot Learning for Software Vulnerability Detection [38.083049237330826]
  This study explores the use of Large Language Models (LLMs) in software vulnerability assessment by simulating the identification of Python code with known Common Weaknessions (CWEs)<n>Our results indicate that while zero-shot prompting performs poorly, few-shot prompting significantly enhances classification performance.<n> challenges such as model reliability, interpretability, and adversarial robustness remain critical areas for future research.
  arXiv  Detail & Related papers  (2025-06-11T18:43:51Z)
• 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)
• Deep-Learning-Directed Preventive Dynamic Security Control via Coordinated Demand Response [0.0]
  Three-phase short-circuit faults in power systems pose significant challenges.<n>These faults can lead to out-of-step (OOS) conditions and jeopardize the system's dynamic security.<n>This paper proposes an end-to-end deep-learning-based mechanism, namely, a convolutional neural network with an attention mechanism, to predict OOS conditions early and enhance the system's fault resilience.
  arXiv  Detail & Related papers  (2025-04-05T04:46:36Z)
• 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)
• Dynamic Vulnerability Criticality Calculator for Industrial Control Systems [0.0]
  This paper introduces an innovative approach by proposing a dynamic vulnerability criticality calculator. Our methodology encompasses the analysis of environmental topology and the effectiveness of deployed security mechanisms. Our approach integrates these factors into a comprehensive Fuzzy Cognitive Map model, incorporating attack paths to holistically assess the overall vulnerability score.
  arXiv  Detail & Related papers  (2024-03-20T09:48:47Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)
• Embodied Laser Attack:Leveraging Scene Priors to Achieve Agent-based Robust Non-contact Attacks [13.726534285661717]
  This paper introduces the Embodied Laser Attack (ELA), a novel framework that dynamically tailors non-contact laser attacks. For the perception module, ELA has innovatively developed a local perspective transformation network, based on the intrinsic prior knowledge of traffic scenes. For the decision and control module, ELA trains an attack agent with data-driven reinforcement learning instead of adopting time-consuming algorithms.
  arXiv  Detail & Related papers  (2023-12-15T06:16:17Z)
• Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications [58.06882713631082]
  Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks raises serious security concerns. This paper proposes an efficient attention-based defense mechanism that exploits adversarial channel-attention to quickly identify and track malicious objects in shallow network layers. It also introduces an efficient multi-frame defense framework, validating its efficacy through extensive experiments aimed at evaluating both defense performance and computational cost.
  arXiv  Detail & Related papers  (2023-11-19T00:47:17Z)
• Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning [91.13113161754022]
  We introduce timing-based adversarial strategies against a DRL-based navigation system by jamming in physical noise patterns on the selected time frames. Our experimental results show that the adversarial timing attacks can lead to a significant performance drop.
  arXiv  Detail & Related papers  (2020-02-20T21:39:25Z)
• Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift [62.997667081978825]
  Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise.
  arXiv  Detail & Related papers  (2020-01-13T13:54:36Z)

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.