Copertina

Optimistic Verifiable Training by Controlling Hardware Nondeterminism

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Srivastava, Megha, Arora, Simran, Boneh, Dan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FairProof : Confidential and Certifiable Fairness for Neural Networks
di: Yadav, Chhavi, et al.
Pubblicazione: (2024)

ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
di: Yadav, Chhavi, et al.
Pubblicazione: (2025)

Hawkeye: Reproducing GPU-Level Non-Determinism
di: Badash, Erez, et al.
Pubblicazione: (2026)

A Factored MDP Approach To Moving Target Defense With Dynamic Threat Modeling and Cost Efficiency
di: Bose, Megha, et al.
Pubblicazione: (2024)

Locking Machine Learning Models into Hardware
di: Clifford, Eleanor, et al.
Pubblicazione: (2024)

SoK: Verifiable Cross-Silo FL
di: Korneev, Aleksei, et al.
Pubblicazione: (2024)

TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks
di: Yao, Jianzhu, et al.
Pubblicazione: (2025)

An AI Architecture with the Capability to Classify and Explain Hardware Trojans
di: Whitten, Paul, et al.
Pubblicazione: (2024)

FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning
di: Gu, Chen, et al.
Pubblicazione: (2025)

A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning
di: Peng, Zhizhi, et al.
Pubblicazione: (2025)

No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning
di: Diana, Francesco, et al.
Pubblicazione: (2026)

NANOZK: Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference
di: Wang, Zhaohui Geoffrey
Pubblicazione: (2026)

Uncertainty-Aware Hardware Trojan Detection Using Multimodal Deep Learning
di: Vishwakarma, Rahul, et al.
Pubblicazione: (2024)

SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
di: Wang, Zeng, et al.
Pubblicazione: (2025)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
di: Srivastava, Saksham Sahai, et al.
Pubblicazione: (2025)

TrustChain: A Blockchain Framework for Auditing and Verifying Aggregators in Decentralized Federated Learning
di: Hallaji, Ehsan, et al.
Pubblicazione: (2025)

Trustworthy Blockchain-based Federated Learning for Electronic Health Records: Securing Participant Identity with Decentralized Identifiers and Verifiable Credentials
di: Tertulino, Rodrigo, et al.
Pubblicazione: (2026)

HW-V2W-Map: Hardware Vulnerability to Weakness Mapping Framework for Root Cause Analysis with GPT-assisted Mitigation Suggestion
di: Lin, Yu-Zheng, et al.
Pubblicazione: (2023)

Adaptive Discounting of Training Time Attacks
di: Bector, Ridhima, et al.
Pubblicazione: (2024)

Extracting Memorized Training Data via Decomposition
di: Su, Ellen, et al.
Pubblicazione: (2024)

Leveraging RAG for Training-Free Alignment of LLMs
di: Halloran, John T.
Pubblicazione: (2026)

Information Theoretic Adversarial Training of Large Language Models
di: Zhang, Yiwei, et al.
Pubblicazione: (2026)

Backdoor Detection through Replicated Execution of Outsourced Training
di: Jia, Hengrui, et al.
Pubblicazione: (2025)

The Autonomy Tax: Defense Training Breaks LLM Agents
di: Li, Shawn, et al.
Pubblicazione: (2026)

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
di: Cheng, Zelei, et al.
Pubblicazione: (2024)

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training
di: Zhang, Yuxiang, et al.
Pubblicazione: (2024)

Defending Against Unforeseen Failure Modes with Latent Adversarial Training
di: Casper, Stephen, et al.
Pubblicazione: (2024)

Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
di: Beerens, Lucas, et al.
Pubblicazione: (2025)

Training RL Agents for Multi-Objective Network Defense Tasks
di: Molina-Markham, Andres, et al.
Pubblicazione: (2025)

NPAT Null-Space Projected Adversarial Training Towards Zero Deterioration
di: Hu, Hanyi, et al.
Pubblicazione: (2024)

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
di: Wang, Bo, et al.
Pubblicazione: (2026)

Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training
di: Yi, Bongsoo, et al.
Pubblicazione: (2024)

FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks
di: Lorenz, Tobias, et al.
Pubblicazione: (2024)

Research on Key Technologies for Cross-Cloud Federated Training of Large Language Models
di: Yang, Haowei, et al.
Pubblicazione: (2024)

Reconstructing Training Data from Adapter-based Federated Large Language Models
di: Chen, Silong, et al.
Pubblicazione: (2026)

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
di: Zhao, Mengnan, et al.
Pubblicazione: (2026)

Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
di: Wang, Yisen, et al.
Pubblicazione: (2025)

Similarity-based Label Inference Attack against Training and Inference of Split Learning
di: Liu, Junlin, et al.
Pubblicazione: (2022)

Aggressive Compression Enables LLM Weight Theft
di: Brown, Davis, et al.
Pubblicazione: (2026)

Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models
di: Wang, Jeffrey G., et al.
Pubblicazione: (2024)