Onyx: Cost-Efficient Disk-Oblivious ANN Search

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rathee, Deevashwer, Watson, Jean-Luc, Zhao, Zirui Neil, Suh, G. Edward, Popa, Raluca Ada
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MPC-Minimized Secure LLM Inference
di: Rathee, Deevashwer, et al.
Pubblicazione: (2024)

Opal: Private Memory for Personal AI
di: Kaviani, Darya, et al.
Pubblicazione: (2026)

A Framework for Evaluating Emerging Cyberattack Capabilities of AI
di: Rodriguez, Mikel, et al.
Pubblicazione: (2025)

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
di: Lu, Yu-An, et al.
Pubblicazione: (2026)

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
di: Zhu, Jinhao, et al.
Pubblicazione: (2025)

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
di: Li, Nanxi, et al.
Pubblicazione: (2025)

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
di: Zhu, Xiaoyuan, et al.
Pubblicazione: (2025)

diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories
di: Guépin, Florent, et al.
Pubblicazione: (2026)

A Relay-Chain-Powered Ciphertext-Policy Attribute-Based Encryption in Intelligent Transportation Systems
di: Singh, Aparna, et al.
Pubblicazione: (2025)

Web Agents Should Adopt the Plan-Then-Execute Paradigm
di: Piet, Julien, et al.
Pubblicazione: (2026)

Towards Reinforcement Learning for Exploration of Speculative Execution Vulnerabilities
di: Lai, Evan, et al.
Pubblicazione: (2025)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
di: Xiang, Chong, et al.
Pubblicazione: (2026)

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
di: Liu, Xiaogeng, et al.
Pubblicazione: (2026)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
di: Li, Hao, et al.
Pubblicazione: (2026)

VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
di: Li, MingSheng, et al.
Pubblicazione: (2025)

Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search
di: Hammar, Kim, et al.
Pubblicazione: (2024)

Decaf: Improving Neural Decompilation with Automatic Feedback and Search
di: Shypula, Alexander, et al.
Pubblicazione: (2026)

CAHS-Attack: CLIP-Aware Heuristic Search Attack Method for Stable Diffusion
di: Xia, Shuhan, et al.
Pubblicazione: (2025)

Membrane: A Cryptographic Access Control System for Data Lakes
di: Kumar, Sam, et al.
Pubblicazione: (2025)

PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
di: Li, Hongwei, et al.
Pubblicazione: (2025)

BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing
di: Kaplan, Caelin, et al.
Pubblicazione: (2025)

Adaptive and Robust Cost-Aware Proof of Quality for Decentralized LLM Inference Networks
di: Tian, Arther, et al.
Pubblicazione: (2026)

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities
di: Yang, Nanzi, et al.
Pubblicazione: (2026)

AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
di: Zhang, Ruisi, et al.
Pubblicazione: (2025)

Information-Dense Reasoning for Efficient and Auditable Security Alert Triage
di: Zhao, Guangze, et al.
Pubblicazione: (2025)

Small Language Models for Phishing Website Detection: Cost, Performance, and Privacy Trade-Offs
di: Goldenits, Georg, et al.
Pubblicazione: (2025)

Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
di: Chen, Huajie, et al.
Pubblicazione: (2026)

Semantic-Aware Parsing for Security Logs
di: Piet, Julien, et al.
Pubblicazione: (2025)

A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage
di: Yang, Huan, et al.
Pubblicazione: (2024)

Secure Multiparty Generative AI
di: Shrestha, Manil, et al.
Pubblicazione: (2024)

BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
di: Yan, Xiaobei, et al.
Pubblicazione: (2025)

Communication Cost Reduction for Subgraph Counting under Local Differential Privacy via Hash Functions
di: Hillebrand, Quentin, et al.
Pubblicazione: (2023)

Nimbus: Secure and Efficient Two-Party Inference for Transformers
di: Li, Zhengyi, et al.
Pubblicazione: (2024)

PromptLocate: Localizing Prompt Injection Attacks
di: Jia, Yuqi, et al.
Pubblicazione: (2025)

Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models
di: Malmqvist, Lars
Pubblicazione: (2025)

MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation
di: Zhao, Yizhe, et al.
Pubblicazione: (2026)

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
di: Shen, Zeyu, et al.
Pubblicazione: (2025)

SecInfer: Preventing Prompt Injection via Inference-time Scaling
di: Liu, Yupei, et al.
Pubblicazione: (2025)

DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
di: Liu, Yupei, et al.
Pubblicazione: (2025)

The Path To Autonomous Cyber Defense
di: Oesch, Sean, et al.
Pubblicazione: (2024)