Copertina

TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Tong, Jiang, Bowen, Lin, Hailong, Li, Borui, Teng, Yixiao, Gao, Yi, Dong, Wei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SPOILER: TEE-Shielded DNN Partitioning of On-Device Secure Inference with Poison Learning
di: Kang, Donghwa, et al.
Pubblicazione: (2026)

Amulet: Fast TEE-Shielded Inference for On-Device Model Protection
di: Mao, Zikai, et al.
Pubblicazione: (2025)

Vulnerabilities in Partial TEE-Shielded LLM Inference with Precomputed Noise
di: Saini, Abhishek, et al.
Pubblicazione: (2026)

TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing
di: Han, Husheng, et al.
Pubblicazione: (2024)

ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
di: Liu, Ruixuan, et al.
Pubblicazione: (2024)

AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
di: Wang, Yu, et al.
Pubblicazione: (2024)

SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment
di: Nayan, Tushar, et al.
Pubblicazione: (2025)

SelectiveShield: Lightweight Hybrid Defense Against Gradient Leakage in Federated Learning
di: Li, Borui, et al.
Pubblicazione: (2025)

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
di: Chen, Zhaorun, et al.
Pubblicazione: (2025)

ShieldBypass: On the Persistence of Impedance Leakage Beyond EM Shielding
di: Awal, Md Sadik, et al.
Pubblicazione: (2026)

UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
di: Xue, Lulu, et al.
Pubblicazione: (2026)

ShieldMMU: Detecting and Defending against Controlled-Channel Attacks in Shielding Memory System
di: Liu, Gang, et al.
Pubblicazione: (2025)

TRUST: A Toolkit for TEE-Assisted Secure Outsourced Computation over Integers
di: Zhao, Bowen, et al.
Pubblicazione: (2024)

Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations
di: Li, Yue, et al.
Pubblicazione: (2025)

ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
di: Pang, Kaiyi, et al.
Pubblicazione: (2024)

Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices
di: Xie, Xueshuo, et al.
Pubblicazione: (2024)

BridgeShield: Enhancing Security for Cross-chain Bridge Applications via Heterogeneous Graph Mining
di: Lin, Dan, et al.
Pubblicazione: (2025)

MirageNet:A Secure, Efficient, and Scalable On-Device Model Protection in Heterogeneous TEE and GPU System
di: Zheng, Huadi, et al.
Pubblicazione: (2026)

Shielding Latent Face Representations From Privacy Attacks
di: Kaushik, Arjun Ramesh, et al.
Pubblicazione: (2025)

QuantumShield: Multilayer Fortification for Quantum Federated Learning
di: Gurung, Dev, et al.
Pubblicazione: (2025)

PromptShield: Deployable Detection for Prompt Injection Attacks
di: Jacob, Dennis, et al.
Pubblicazione: (2025)

AmbShield: Enhancing Physical Layer Security with Ambient Backscatter Devices against Eavesdroppers
di: Zhang, Yifan, et al.
Pubblicazione: (2026)

ARMOR: Shielding Unlearnable Examples against Data Augmentation
di: Gong, Xueluan, et al.
Pubblicazione: (2025)

Styx: Collaborative and Private Data Processing With TEE-Enforced Sticky Policy
di: Zhao, Shixuan, et al.
Pubblicazione: (2026)

AgenTEE: Confidential LLM Agent Execution on Edge Devices
di: Abdollahi, Sina, et al.
Pubblicazione: (2026)

Shielded but Lightweight: Building Practical Confidential Containers with ARM CCA
di: Song, Liantao, et al.
Pubblicazione: (2026)

Peering Behind the Shield: Guardrail Identification in Large Language Models
di: Yang, Ziqing, et al.
Pubblicazione: (2025)

CCxTrust: Confidential Computing Platform Based on TEE and TPM Collaborative Trust
di: Shang, Ketong, et al.
Pubblicazione: (2024)

BlindexTEE: A Blind Index Approach towards TEE-supported End-to-end Encrypted DBMS
di: Vialar, Louis, et al.
Pubblicazione: (2024)

Optimistic TEE-Rollups: A Hybrid Architecture for Scalable and Verifiable Generative AI Inference on Blockchain
di: Chan, Aaron, et al.
Pubblicazione: (2025)

NodeShield: Runtime Enforcement of Security-Enhanced SBOMs for Node.js
di: Cornelissen, Eric, et al.
Pubblicazione: (2025)

Trusted-Execution Environment (TEE) for Solving the Replication Crisis in Academia
di: Li, Jiasun, et al.
Pubblicazione: (2026)

CallShield: Secure Caller Authentication over Real-Time Audio Channels
di: Rabh, Mouna, et al.
Pubblicazione: (2026)

PriveShield: Enhancing User Privacy Using Automatic Isolated Profiles in Browsers
di: Akhavani, Seyed Ali, et al.
Pubblicazione: (2025)

TensorCommitments: A Lightweight Verifiable Inference for Language Models
di: Baser, Oguzhan, et al.
Pubblicazione: (2026)

From Texts to Shields: Convergence of Large Language Models and Cybersecurity
di: Li, Tao, et al.
Pubblicazione: (2025)

Safeguarding Smart Inhaler Devices and Patient Privacy in Respiratory Health Monitoring
di: Babajide, Asaju, et al.
Pubblicazione: (2025)

ByteShield: Adversarially Robust End-to-End Malware Detection through Byte Masking
di: Gibert, Daniel, et al.
Pubblicazione: (2025)

RaceTEE: Enabling Interoperability of Confidential Smart Contracts
di: Zhang, Keyu, et al.
Pubblicazione: (2025)

GuaranTEE: Towards Attestable and Private ML with CCA
di: Siby, Sandra, et al.
Pubblicazione: (2024)