{"total":102,"rows":[{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2104.14380","title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","created":"2021-04-29","cited_by_count":93,"area":null},{"id":"2102.08504","title":"Label Leakage and Protection in Two-party Split Learning","created":"2021-02-17","cited_by_count":90,"area":null},{"id":"2205.07424","title":"Trustworthy Graph Neural Networks: Aspects, Methods and Trends","created":"2022-05-16","cited_by_count":89,"area":null},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88,"area":null},{"id":"2204.10836","title":"Federated Learning Enables Big Data for Rare Cancer Boundary Detection","created":"2022-04-22","cited_by_count":84,"area":null},{"id":"2103.06191","title":"A Study of Face Obfuscation in ImageNet","created":"2021-03-10","cited_by_count":83,"area":null},{"id":"2106.01221","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","created":"2021-06-02","cited_by_count":77,"area":null},{"id":"2106.04690","title":"Handcrafted Backdoors in Deep Neural Networks","created":"2021-06-08","cited_by_count":63,"area":null},{"id":"2104.10949","title":"CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU","created":"2021-04-22","cited_by_count":46,"area":null},{"id":"2101.06896","title":"DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection","created":"2021-01-18","cited_by_count":44,"area":null},{"id":"2106.08890","title":"ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection","created":"2021-06-11","cited_by_count":33,"area":null},{"id":"2306.14123","title":"Privacy and Fairness in Federated Learning: on the Perspective of Trade-off","created":"2023-06-25","cited_by_count":26,"area":null},{"id":"2210.09126","title":"Verifiable and Provably Secure Machine Unlearning","created":"2022-10-17","cited_by_count":25,"area":"safety"},{"id":"2310.07152","title":"No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML","created":"2023-10-11","cited_by_count":21,"area":null},{"id":"2107.09898","title":"Defending against Reconstruction Attack in Vertical Federated Learning","created":"2021-07-21","cited_by_count":20,"area":null},{"id":"2202.01971","title":"Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization","created":"2022-02-04","cited_by_count":19,"area":null},{"id":"2106.08475","title":"Circa: Stochastic ReLUs for Private Deep Learning","created":"2021-06-15","cited_by_count":16,"area":null},{"id":"2304.08566","title":"GrOVe: Ownership Verification of Graph Neural Networks using Embeddings","created":"2023-04-17","cited_by_count":16,"area":null},{"id":"2410.11876","title":"Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2208.10134","title":"Machine Learning with Confidential Computing: A Systematization of Knowledge","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2210.11334","title":"Proof of Unlearning: Definitions and Instantiation","created":"2022-10-20","cited_by_count":15,"area":"safety"},{"id":"2105.01281","title":"Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX","created":"2021-05-04","cited_by_count":14,"area":null},{"id":"2107.12342","title":"Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning","created":"2021-07-26","cited_by_count":14,"area":null},{"id":"2207.00083","title":"DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware","created":"2022-06-30","cited_by_count":14,"area":null},{"id":"2101.08204","title":"secureTF: A Secure TensorFlow Framework","created":"2021-01-20","cited_by_count":12,"area":null},{"id":"2301.12195","title":"BAFFLE: A Baseline of Backpropagation-Free Federated Learning","created":"2023-01-28","cited_by_count":12,"area":null},{"id":"2205.03884","title":"Decentralized Stochastic Optimization with Inherent Privacy Protection","created":"2022-05-08","cited_by_count":11,"area":null},{"id":"2404.11121","title":"TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment","created":"2024-04-17","cited_by_count":11,"area":null},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2212.05428","title":"ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipeline","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2304.12889","title":"Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Things","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2205.13722","title":"Can Foundation Models Help Us Achieve Perfect Secrecy?","created":"2022-05-27","cited_by_count":9,"area":null},{"id":"2105.09400","title":"Separation of Powers in Federated Learning","created":"2021-05-19","cited_by_count":8,"area":null},{"id":"2302.12150","title":"A Survey of Secure Computation Using Trusted Execution Environments","created":"2023-02-23","cited_by_count":8,"area":null},{"id":"2401.09796","title":"A Fast, Performant, Secure Distributed Training Framework For Large Language Model","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2202.11655","title":"TEE-based decentralized recommender systems: The raw data sharing redemption","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2307.15017","title":"Samplable Anonymous Aggregation for Private Federated Data Analysis","created":"2023-07-27","cited_by_count":6,"area":null},{"id":"2102.00921","title":"Forensicability of Deep Neural Network Inference Pipelines","created":"2021-02-01","cited_by_count":5,"area":null},{"id":"2109.09868","title":"ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems","created":"2021-09-20","cited_by_count":5,"area":null},{"id":"2208.05895","title":"Shielding Federated Learning Systems against Inference Attacks with ARM TrustZone","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2404.13475","title":"PristiQ: A Co-Design Framework for Preserving Data Security of Quantum Learning in the Cloud","created":"2024-04-20","cited_by_count":5,"area":null},{"id":"2410.13903","title":"CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2509.18886","title":"Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2107.12958","title":"Adaptive Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning","created":"2021-07-27","cited_by_count":4,"area":null},{"id":"2111.03308","title":"Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspective","created":"2021-11-05","cited_by_count":4,"area":null},{"id":"2209.13643","title":"MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inference","created":"2022-09-27","cited_by_count":4,"area":null},{"id":"2212.11810","title":"GAN-based Domain Inference Attack","created":"2022-12-22","cited_by_count":4,"area":null},{"id":"2312.05264","title":"All Rivers Run to the Sea: Private Learning with Asymmetric Flows","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2410.05930","title":"Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2508.05691","title":"SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2603.05786","title":"Proof-of-Guardrail in AI Agents and What (Not) to Trust from It","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2104.02987","title":"Plinius: Secure and Persistent Machine Learning Model Training","created":"2021-04-07","cited_by_count":3,"area":null},{"id":"2203.10923","title":"TinyMLOps: Operational Challenges for Widespread Edge AI Adoption","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2411.09945","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","created":"2024-11-15","cited_by_count":3,"area":null},{"id":"2512.16317","title":"Design and Evaluation of Cost-Aware PoQ for Decentralized LLM Inference","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2604.24203","title":"Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing","created":"2026-04-27","cited_by_count":3,"area":"agents"},{"id":"2605.29524","title":"KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2103.16898","title":"Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Support","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2203.07728","title":"Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approach","created":"2022-03-15","cited_by_count":2,"area":null},{"id":"2205.09005","title":"Confidential Machine Learning within Graphcore IPUs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2302.06361","title":"Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits","created":"2023-02-13","cited_by_count":2,"area":null},{"id":"2401.11531","title":"Tempo: Confidentiality Preservation in Cloud-Based Neural Network Training","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2506.20915","title":"ZKPROV: A Zero-Knowledge Approach to Dataset Provenance for Large Language Models","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2507.03278","title":"Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Accelerators","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2509.11555","title":"Dstack: A Zero Trust Framework for Confidential Containers","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2510.19979","title":"SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2603.01499","title":"Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2104.02261","title":"Enabling Inference Privacy with Adaptive Noise Injection","created":"2021-04-06","cited_by_count":1,"area":null},{"id":"2306.03600","title":"Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations","created":"2023-06-06","cited_by_count":1,"area":"safety"},{"id":"2403.10995","title":"Edge Private Graph Neural Networks with Singular Value Perturbation","created":"2024-03-16","cited_by_count":1,"area":null},{"id":"2405.16361","title":"LDPKiT: Superimposing Remote Queries for Privacy-Preserving Distillation","created":"2024-05-25","cited_by_count":1,"area":null},{"id":"2406.00586","title":"VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devices","created":"2024-06-02","cited_by_count":1,"area":null},{"id":"2505.08793","title":"Onboard Optimization and Learning: A Survey","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2509.09091","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","created":"2025-09-11","cited_by_count":1,"area":"inference"},{"id":"2510.16028","title":"TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2603.02214","title":"Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.30040","title":"Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.16358","title":"The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2607.29221","title":"MOSAIC: Masked Outsourcing of Secure AI Computations","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2105.00334","title":"Privacy and Integrity Preserving Training Using Trusted Hardware","created":"2021-05-01","cited_by_count":0,"area":null},{"id":"2111.03125","title":"Secure Machine Learning in the Cloud Using One Way Scrambling by Deconvolution","created":"2021-11-04","cited_by_count":0,"area":null},{"id":"2301.00252","title":"A Comparative Study of Image Disguising Methods for Confidential Outsourced Learning","created":"2022-12-31","cited_by_count":0,"area":null},{"id":"2304.00083","title":"A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2308.00963","title":"Integrating Homomorphic Encryption and Trusted Execution Technology for Autonomous and Confidential Model Refining in Cloud","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2403.12568","title":"Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices","created":"2024-03-19","cited_by_count":0,"area":null},{"id":"2412.08534","title":"Protecting Confidentiality, Privacy and Integrity in Collaborative Learning","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2507.02376","title":"On the Inference (In-)Security of Vertical Federated Learning: Efficient Auditing against Inference Tampering Attack","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2603.20504","title":"Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.23205","title":"Tessera: Secure, Near-Line-Rate Weight Streaming for UMA Edge Accelerators","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.03213","title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2606.04317","title":"Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.16352","title":"Communication-Efficient Verifiable Attention for LLM Inference","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.16461","title":"Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.19490","title":"Integrity of peer-to-peer distributed LLM inference under malicious nodes","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.16868","title":"Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22716","title":"TEE-X: TEE-aware Acceleration Framework for Large Vision Models at the Edge","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.10264","title":"Maverick: Private and Verifiable LLM Inference Made Practical via Matrix-Vector Multiplication Delegation","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.15039","title":"SpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":"100"}