# Runtime Detection of Adversarial Attacks in AI Accelerators Using Performance Counters

arXiv: https://arxiv.org/abs/2503.07568 · HTML: https://mlsanity.com/paper/2503.07568/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks](https://mlsanity.com/paper/1810.03487/) (2018)
- [A Unified Hardware-based Threat Detector for AI Accelerators](https://mlsanity.com/paper/2311.16684/) (2023)

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

- [Architectural Design and Performance Analysis of FPGA based AI Accelerators: A Comprehensive Review](https://mlsanity.com/paper/2603.08740/) (2026)

## Abstract (arXiv)

Rapid adoption of AI technologies raises several major security concerns, including the risks of adversarial perturbations, which threaten the confidentiality and integrity of AI applications. Protecting AI hardware from misuse and diverse security threats is a challenging task. To address this challenge, we propose SAMURAI, a novel framework for safeguarding against malicious usage of AI hardware and its resilience to attacks. SAMURAI introduces an AI Performance Counter (APC) for tracking dynamic behavior of an AI model coupled with an on-chip Machine Learning (ML) analysis engine, known as TANTO (Trained Anomaly Inspection Through Trace Observation). APC records the runtime profile of the low-level hardware events of different AI operations. Subsequently, the summary information recorded by the APC is processed by TANTO to efficiently identify potential security breaches and ensure secure, responsible use of AI. SAMURAI enables real-time detection of security threats and misuse without relying on traditional software-based solutions that require model integration. Experimental results demonstrate that SAMURAI achieves up to 97% accuracy in detecting adversarial attacks with moderate overhead on various AI models, significantly outperforming conventional software-based approaches. It enhances security and regulatory compliance, providing a comprehensive solution for safeguarding AI against emergent threats.