Attacking AI Accelerators by Leveraging Arithmetic Properties of Addition

• URL: http://arxiv.org/abs/2603.27439v1
• Date: Sat, 28 Mar 2026 23:03:27 GMT
• Title: Attacking AI Accelerators by Leveraging Arithmetic Properties of Addition
• Abstract summary: We present a new hardware aging attack that exploits commutative properties of addition to disrupt the multiply-and-add operation.<n>By permuting the inputs of an adder, the attack preserves functional correctness while inducing unbalanced stress among transistors, accelerating delay degradation in the circuit.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The dependability of AI models relies largely on the reliability of the underlying computation hardware. Hardware aging attacks can compromise the computing substrate and disrupt AI models over the long run. In this work, we present a new hardware aging attack that exploits commutative properties of addition to disrupt the multiply-and-add operation that forms the backbone of almost all AI models. By permuting the inputs of an adder, the attack preserves functional correctness while inducing unbalanced stress among transistors, accelerating delay degradation in the circuit. Unlike prior approaches that rely on input manipulation, additional trojan circuitry, etc., the proposed method incurs virtually no area or software overhead. Experimental results with two types of multipliers, different bit widths, a mix of AI models and datasets demonstrates that the proposed attack degrades inference accuracy by up to 64% in 4 years, posing a significant threat to AI accelerators. The attack can also be extended to arithmetic units of general-purpose processors.

Related papers

• Building Reliable Arithmetic Multipliers Under NBTI Aging and Process Variations [0.0]
  We focus on the aging of arithmetic multipliers, which are a cornerstone of modern computing systems.<n>In particular, AI workloads can accelerate Negative Bias Temperature Instability (NBTI) effects in multipliers.<n>This paper presents a novel aging mitigation technique that leverages the signinvariance property of multiplication.
  arXiv  Detail & Related papers  (2026-05-18T14:12:01Z)
• Stealing AI Model Weights Through Covert Communication Channels [0.0]
  We present a novel attack targeting wireless devices equipped with AI hardware accelerators.<n>In the first phase, the victim's device is compromised with a hardware Trojan.<n>In the second phase, the adversary uses a nearby wireless device to intercept the victim's transmission frames.
  arXiv  Detail & Related papers  (2025-09-30T18:21:41Z)
• Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations [0.0]
  This paper introduces a novel parallel discrete event simulation (PDES) based methodology to combine multiple AI and non-AI agents.<n>We evaluate our approach by solving four problems from four different domains and comparing the results with those from AI models alone.<n>Results show that overall accuracy of our approach is 68% where as the accuracy of vanilla models is less than 23%.
  arXiv  Detail & Related papers  (2025-05-28T17:50:01Z)
• Generative Diffusion-based Contract Design for Efficient AI Twins Migration in Vehicular Embodied AI Networks [55.15079732226397]
  Embodied AI is a rapidly advancing field that bridges the gap between cyberspace and physical space. In VEANET, embodied AI twins act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving.
  arXiv  Detail & Related papers  (2024-10-02T02:20:42Z)
• Enhancing Adversarial Transferability with Adversarial Weight Tuning [50.01825144613307]
  adversarial examples (AEs) mislead the model while appearing benign to human observers.<n>AWT is a data-free tuning method that combines gradient-based and model-based attack methods to enhance the transferability of AEs.
  arXiv  Detail & Related papers  (2024-08-18T13:31:26Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• AI Algorithm for Predicting and Optimizing Trajectory of UAV Swarm [4.025253632495535]
  This paper explores the application of Artificial Intelligence (AI) techniques for generating fleets of Unmanned Aerial Vehicles (UAVs) The two main challenges addressed include accurately predicting the paths of UAVs and efficiently avoiding collisions between them. We introduce a novel activation function, AdaptoSwelliGauss, which is a sophisticated fusion of Swish and Elliott activations.
  arXiv  Detail & Related papers  (2024-05-20T01:47:28Z)
• Adaptation of XAI to Auto-tuning for Numerical Libraries [0.0]
  Explainable AI (XAI) technology is gaining prominence, aiming to streamline AI model development and alleviate the burden of explaining AI outputs to users. This research focuses on XAI for AI models when integrated into two different processes for practical numerical computations.
  arXiv  Detail & Related papers  (2024-05-12T09:00:56Z)
• Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attacks [7.500941533148728]
  We propose a cloud-based service framework that encapsulates computing components and assessment tasks into pipelines. We demonstrate the application of XAI services for assessing five quality attributes of AI models.
  arXiv  Detail & Related papers  (2024-01-22T00:37:01Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• Composite Adversarial Attacks [57.293211764569996]
  Adversarial attack is a technique for deceiving Machine Learning (ML) models. In this paper, a new procedure called Composite Adrial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms. CAA beats 10 top attackers on 11 diverse defenses with less elapsed time.
  arXiv  Detail & Related papers  (2020-12-10T03:21:16Z)
• On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems [62.997667081978825]
  We present a formal framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. The first class involves adversarial examples and concerns the introduction of small perturbations of the input data that cause misclassification. The second class, introduced here for the first time and named stealth attacks, involves small perturbations to the AI system itself.
  arXiv  Detail & Related papers  (2020-04-09T10:56:53Z)

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.