paper-with-me

Papers

Enhancing TinyML Security: Study of Adversarial Attack Transferability

2024-07-16 · Parin Shah, Yuvaraj Govindarajulu, Pavan Kulkarni, Manojkumar Parmar

The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence on cloud connections. While TinyML offers real-time data analysis and swift responses critical for diverse applications, its devices' intrinsic resource limitations expose them to security risks. This research delves into the adversarial vulnerabilities of AI models on resource-constrained embedded hardware, with a focus on Model Extraction and Evasion Attacks. Our findings reveal that adversarial attacks from powerful host machines could be transferred to smaller, less secure devices like ESP32 and Raspberry Pi. This illustrates that adversarial attacks could be extended to tiny devices, underscoring vulnerabilities, and emphasizing the necessity for reinforced security measures in TinyML deployments. This exploration enhances the comprehension of security challenges in TinyML and offers insights for safeguarding sensitive data and ensuring device dependability in AI-powered edge computing settings.

📄 PDF Abstract BibTeX arXiv:2407.11599

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackEdge-computingModel extraction

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems

2024-11-11 · Jacob Huckelberry, Yuke Zhang, Allison Sansone, James Mickens 외

Tiny Machine Learning (TinyML) systems, which enable machine learning inference on highly resource-constrained devices, are transforming edge computing but encounter unique security challenges. These devices, restricted …

CPUEdge-computing

TinyML-Driven Cybersecurity for Autonomous Spacecraft: Latency-Accuracy Analysis for SPARTA RF and Cyber Threat Detection

2026-06-04 · Van Le, Trevor Tran, Tan Le arxiv

Autonomous spacecraft require rapid, lightweight, and reliable onboard detection of cyber-RF threats. Using the SPARTA attack model, we analyze the latency-accuracy trade-offs of TinyML-compatible classical models -- Ran…

Development of an Edge Resilient ML Ensemble to Tolerate ICS Adversarial Attacks

2024-09-26 · Likai Yao, Qinxuan Shi, Zhanglong Yang, Sicong Shao 외

Deploying machine learning (ML) in dynamic data-driven applications systems (DDDAS) can improve the security of industrial control systems (ICS). However, ML-based DDDAS are vulnerable to adversarial attacks because adve…

Privacy Preserving

On TinyML and Cybersecurity: Electric Vehicle Charging Infrastructure Use Case

2024-04-25 · Fatemeh Dehrouyeh, Li Yang, Firouz Badrkhani Ajaei, Abdallah Shami

As technology advances, the use of Machine Learning (ML) in cybersecurity is becoming increasingly crucial to tackle the growing complexity of cyber threats. While traditional ML models can enhance cybersecurity, their h…

Transfer Learning

Optimizing Key-Selection for Face-based One-Time Biometrics via Morphing

2023-10-04 · Daile Osorio-Roig, Mahdi Ghafourian, Christian Rathgeb, Ruben Vera-Rodriguez 외

Nowadays, facial recognition systems are still vulnerable to adversarial attacks. These attacks vary from simple perturbations of the input image to modifying the parameters of the recognition model to impersonate an aut…

Adversarial AttackBlockingFace Recognition