Imagen de Portada

Split-and-Denoise: Protect large language model inference with local differential privacy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mai, Peihua, Yan, Ran, Huang, Zhe, Yang, Youjia, Pang, Yan
Formato:	Preprint
Publicado:	2023
Materias:	Artificial Intelligence Cryptography and Security I.2.7
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ConfusionPrompt: Practical Private Inference for Online Large Language Models
por: Mai, Peihua, et al.
Publicado: (2023)

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
por: Mai, Peihua, et al.
Publicado: (2025)

AI Safeguards, Generative AI and the Pandora Box: AI Safety Measures to Protect Businesses and Personal Reputation
por: Kumar, Prasanna
Publicado: (2026)

Efficient LLM Safety Evaluation through Multi-Agent Debate
por: Lin, Dachuan, et al.
Publicado: (2025)

Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models
por: Del Rosario, Ron F.
Publicado: (2025)

Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents
por: Patlan, Atharv Singh, et al.
Publicado: (2025)

Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously
por: Adiletta, Andrew, et al.
Publicado: (2025)

Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
por: Young, Richard J.
Publicado: (2025)

DWFS-Obfuscation: Dynamic Weighted Feature Selection for Robust Malware Familial Classification under Obfuscation
por: Wei, Xingyuan, et al.
Publicado: (2025)

POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
por: Shao, Yangguang, et al.
Publicado: (2025)

Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible
por: Zhao, Lepeng, et al.
Publicado: (2026)

Mitigating Trojanized Prompt Chains in Educational LLM Use Cases: Experimental Findings and Detection Tool Design
por: Charles, Richard M., et al.
Publicado: (2025)

CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
por: Zhu, Yuxuan, et al.
Publicado: (2025)

Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
por: Xin, Yuan, et al.
Publicado: (2025)

Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache
por: Wang, Xinhai, et al.
Publicado: (2026)

PromptSAM+: Malware Detection based on Prompt Segment Anything Model
por: Wei, Xingyuan, et al.
Publicado: (2024)

Large Language Models are Advanced Anonymizers
por: Staab, Robin, et al.
Publicado: (2024)

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
por: Miculicich, Lesly, et al.
Publicado: (2025)

Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts
por: Downey-Webb, Tiarnaigh, et al.
Publicado: (2025)

Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems
por: Pai, Aaditya
Publicado: (2026)

Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems
por: Hackett, William, et al.
Publicado: (2025)

JavelinGuard: Low-Cost Transformer Architectures for LLM Security
por: Datta, Yash, et al.
Publicado: (2025)

Mitigating the Impact of Malware Evolution on API Sequence-based Windows Malware Detector
por: Wei, Xingyuan, et al.
Publicado: (2024)

Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
por: Kurian, Ashley, et al.
Publicado: (2025)

Vertical Federated Graph Neural Network for Recommender System
por: Mai, Peihua, et al.
Publicado: (2023)

Reducing Information Overload: Because Even Security Experts Need to Blink
por: Kuehn, Philipp, et al.
Publicado: (2022)

AlignDP: Hybrid Differential Privacy with Rarity-Aware Protection for LLMs
por: Gaikwad, Madhava
Publicado: (2025)

sudoLLM: On Multi-role Alignment of Language Models
por: Saha, Soumadeep, et al.
Publicado: (2025)

UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
por: Geng, Runpeng, et al.
Publicado: (2025)

Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)
por: Verma, Apurv, et al.
Publicado: (2024)

Send to which account? Evaluation of an LLM-based Scambaiting System
por: Siadati, Hossein, et al.
Publicado: (2025)

MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
por: Pan, Leyi, et al.
Publicado: (2025)

Detecting Prompt Injection Attacks Against Application Using Classifiers
por: Shaheer, Safwan, et al.
Publicado: (2025)

Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps
por: Chona, Alankrit, et al.
Publicado: (2026)

Guardians of the Web: The Evolution and Future of Website Information Security
por: Islam, Md Saiful, et al.
Publicado: (2025)

Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks
por: Shaheer, Safwan, et al.
Publicado: (2025)

Measuring Harmfulness of Computer-Using Agents
por: Tian, Aaron Xuxiang, et al.
Publicado: (2025)

Countermind: A Multi-Layered Security Architecture for Large Language Models
por: Schwarz, Dominik
Publicado: (2025)

Prompt Fencing: A Cryptographic Approach to Establishing Security Boundaries in Large Language Model Prompts
por: Peh, Steven
Publicado: (2025)

Biometrics Employing Neural Network
por: Bhuiyan, Sajjad
Publicado: (2024)