Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms
Fuente:
arXiv
Saved in:
| Main Authors: | Tsiatsikas, Zisis, Fakis, Alexandros, Karopoulos, Georgios, Kouliaridis, Vasileios, Anagnostopoulos, Marios |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Assessing the Effectiveness of LLMs in Android Application Vulnerability Analysis
by: Kouliaridis, Vasileios, et al.
Published: (2024)
by: Kouliaridis, Vasileios, et al.
Published: (2024)
Keep your memory dump shut: Unveiling data leaks in password managers
by: Chatzoglou, Efstratios, et al.
Published: (2024)
by: Chatzoglou, Efstratios, et al.
Published: (2024)
Integrated Simulation Framework for Adversarial Attacks on Autonomous Vehicles
by: Anagnostopoulos, Christos, et al.
Published: (2025)
by: Anagnostopoulos, Christos, et al.
Published: (2025)
Protection against Source Inference Attacks in Federated Learning
by: Athanasiou, Andreas, et al.
Published: (2026)
by: Athanasiou, Andreas, et al.
Published: (2026)
Amulet: Fast TEE-Shielded Inference for On-Device Model Protection
by: Mao, Zikai, et al.
Published: (2025)
by: Mao, Zikai, et al.
Published: (2025)
An Early Experience with Confidential Computing Architecture for On-Device Model Protection
by: Abdollahi, Sina, et al.
Published: (2025)
by: Abdollahi, Sina, et al.
Published: (2025)
Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning
by: Hasan, Syed Mhamudul, et al.
Published: (2025)
by: Hasan, Syed Mhamudul, et al.
Published: (2025)
SynthChain: A Synthetic Benchmark and Forensic Analysis of Advanced and Stealthy Software Supply Chain Attacks
by: Tan, Zhuoran, et al.
Published: (2026)
by: Tan, Zhuoran, et al.
Published: (2026)
LLM-Assisted AHP for Explainable Cyber Range Evaluation
by: Kampourakis, Vyron, et al.
Published: (2025)
by: Kampourakis, Vyron, et al.
Published: (2025)
Protection against Source Inference Attacks in Federated Learning using Unary Encoding and Shuffling
by: Athanasiou, Andreas, et al.
Published: (2024)
by: Athanasiou, Andreas, et al.
Published: (2024)
Co-Evolutionary Defence of Active Directory Attack Graphs via GNN-Approximated Dynamic Programming
by: Goel, Diksha, et al.
Published: (2025)
by: Goel, Diksha, et al.
Published: (2025)
Systematic Literature Review of EM-SCA Attacks on Encryption
by: Zunaidi, Muhammad Rusyaidi, et al.
Published: (2024)
by: Zunaidi, Muhammad Rusyaidi, et al.
Published: (2024)
A Systematic Review on Crimes facilitated by Consumer Internet of Things Devices
by: Brown, Ashley, et al.
Published: (2025)
by: Brown, Ashley, et al.
Published: (2025)
Interpreting Adversarial Attacks and Defences using Architectures with Enhanced Interpretability
by: Rao, Akshay G, et al.
Published: (2025)
by: Rao, Akshay G, et al.
Published: (2025)
Threat-Informed Cyber Resilience Index: A Probabilistic Quantitative Approach to Measure Defence Effectiveness Against Cyber Attacks
by: Alevizos, Lampis, et al.
Published: (2024)
by: Alevizos, Lampis, et al.
Published: (2024)
Categorizing Service Worker Attacks and Mitigations
by: Subramani, Karthika, et al.
Published: (2021)
by: Subramani, Karthika, et al.
Published: (2021)
MarcoPolo: A Zero-Permission Attack for Location Type Inference from the Magnetic Field using Mobile Devices
by: Perez, Beatrice, et al.
Published: (2026)
by: Perez, Beatrice, et al.
Published: (2026)
Serverless AI Security: Attack Surface Analysis and Runtime Protection Mechanisms for FaaS-Based Machine Learning
by: Pathade, Chetan, et al.
Published: (2026)
by: Pathade, Chetan, et al.
Published: (2026)
On Digital Twins in Defence: Overview and Applications
by: Giberna, Marco, et al.
Published: (2025)
by: Giberna, Marco, et al.
Published: (2025)
Attesting LLM Pipelines: Enforcing Verifiable Training and Release Claims
by: Tan, Zhuoran, et al.
Published: (2026)
by: Tan, Zhuoran, et al.
Published: (2026)
A Complexity-Informed Approach to Optimise Cyber Defences
by: Alevizos, Lampis
Published: (2025)
by: Alevizos, Lampis
Published: (2025)
Devlore: Device Interrupt Protection for Confidential VMs
by: Bertschi, Andrin, et al.
Published: (2024)
by: Bertschi, Andrin, et al.
Published: (2024)
Systematic Integration of Digital Twins and Constrained LLMs for Interpretable Cyber-Physical Anomaly Detection
by: Kampourakis, Konstantinos E., et al.
Published: (2026)
by: Kampourakis, Konstantinos E., et al.
Published: (2026)
Auditing Privacy Mechanisms via Label Inference Attacks
by: Busa-Fekete, Róbert István, et al.
Published: (2024)
by: Busa-Fekete, Róbert István, et al.
Published: (2024)
Gait-Based Privacy Protection for Smart Wearable Devices
by: Su, Yu, et al.
Published: (2024)
by: Su, Yu, et al.
Published: (2024)
A UEFI System with SPDM to Protect Against Unauthorized Device Connections
by: de Freitas, Ágatha, et al.
Published: (2026)
by: de Freitas, Ágatha, et al.
Published: (2026)
Energy Cyber Attacks to Smart Healthcare Devices: A Testbed
by: Alwaisi, Zainab, et al.
Published: (2024)
by: Alwaisi, Zainab, et al.
Published: (2024)
Resurrection Attack: Defeating Xilinx MPU's Memory Protection
by: Madabhushi, Bharadwaj, et al.
Published: (2024)
by: Madabhushi, Bharadwaj, et al.
Published: (2024)
Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
by: Nguyen, Quan, et al.
Published: (2025)
by: Nguyen, Quan, et al.
Published: (2025)
Neighborhood Blending: A Lightweight Inference-Time Defense Against Membership Inference Attacks
by: Zafar, Osama, et al.
Published: (2026)
by: Zafar, Osama, et al.
Published: (2026)
DETOUR: A Practical Backdoor Attack against Object Detection
by: Liu, Dazhuang, et al.
Published: (2026)
by: Liu, Dazhuang, et al.
Published: (2026)
HidePrint: Protecting Device Anonymity by Obscuring Radio Fingerprints
by: Oligeri, Gabriele, et al.
Published: (2024)
by: Oligeri, Gabriele, et al.
Published: (2024)
Designing a Secure Device-to-Device File Transfer Mechanism
by: Rahalkar, Chaitanya, et al.
Published: (2024)
by: Rahalkar, Chaitanya, et al.
Published: (2024)
A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
by: Jebreel, Najeeb, et al.
Published: (2026)
by: Jebreel, Najeeb, et al.
Published: (2026)
Detection of Energy Consumption Cyber Attacks on Smart Devices
by: Alwaisi, Zainab, et al.
Published: (2024)
by: Alwaisi, Zainab, et al.
Published: (2024)
Towards Weaknesses and Attack Patterns Prediction for IoT Devices
by: A., Carlos A. Rivera, et al.
Published: (2024)
by: A., Carlos A. Rivera, et al.
Published: (2024)
Prompt Inference Attack on Distributed Large Language Model Inference Frameworks
by: Luo, Xinjian, et al.
Published: (2025)
by: Luo, Xinjian, et al.
Published: (2025)
Operational Runtime Behavior Mining for Open-Source Supply Chain Security
by: Tan, Zhuoran, et al.
Published: (2026)
by: Tan, Zhuoran, et al.
Published: (2026)
Multi-Objective Reinforcement Learning for Automated Resilient Cyber Defence
by: O'Driscoll, Ross, et al.
Published: (2024)
by: O'Driscoll, Ross, et al.
Published: (2024)
A Systematic Review of Poisoning Attacks Against Large Language Models
by: Fendley, Neil, et al.
Published: (2025)
by: Fendley, Neil, et al.
Published: (2025)
Similar Items
-
Assessing the Effectiveness of LLMs in Android Application Vulnerability Analysis
by: Kouliaridis, Vasileios, et al.
Published: (2024) -
Keep your memory dump shut: Unveiling data leaks in password managers
by: Chatzoglou, Efstratios, et al.
Published: (2024) -
Integrated Simulation Framework for Adversarial Attacks on Autonomous Vehicles
by: Anagnostopoulos, Christos, et al.
Published: (2025) -
Protection against Source Inference Attacks in Federated Learning
by: Athanasiou, Andreas, et al.
Published: (2026) -
Amulet: Fast TEE-Shielded Inference for On-Device Model Protection
by: Mao, Zikai, et al.
Published: (2025)