Image de couverture de livre

Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Vaikuntanathan, Vinod, Zamir, Or
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Planting Undetectable Backdoors in Machine Learning Models
par: Goldwasser, Shafi, et autres
Publié: (2022)

Pseudorandom Error-Correcting Codes
par: Christ, Miranda, et autres
Publié: (2024)

Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
par: Golowich, Noah, et autres
Publié: (2024)

An Undetectable Watermark for Generative Image Models
par: Gunn, Sam, et autres
Publié: (2024)

Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
par: Choudhary, Sarthak, et autres
Publié: (2026)

Improving Algorithmic Efficiency using Cryptography
par: Vaikuntanathan, Vinod, et autres
Publié: (2025)

Enhancing Cloud Network Resilience via a Robust LLM-Empowered Multi-Agent Reinforcement Learning Framework
par: Peng, Yixiao, et autres
Publié: (2026)

Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
par: Bazinska, Julia, et autres
Publié: (2025)

AgentGuardian: Learning Access Control Policies to Govern AI Agent Behavior
par: Abaev, Nadya, et autres
Publié: (2026)

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
par: Aremu, Toluwani, et autres
Publié: (2025)

EVMbench: Evaluating AI Agents on Smart Contract Security
par: Wang, Justin, et autres
Publié: (2026)

Detecting Malicious AI Agents Through Simulated Interactions
par: Pi, Yulu, et autres
Publié: (2025)

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
par: Liu, Zhenyu, et autres
Publié: (2024)

XBreaking: Understanding how LLMs security alignment can be broken
par: Arazzi, Marco, et autres
Publié: (2025)

CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
par: Das, Debeshee, et autres
Publié: (2025)

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
par: Wang, Zhun, et autres
Publié: (2026)

Resilience of Entropy Model in Distributed Neural Networks
par: Zhang, Milin, et autres
Publié: (2024)

BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
par: Zhang, Kaiyuan, et autres
Publié: (2025)

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
par: Wang, Zhun, et autres
Publié: (2025)

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
par: Guo, Qiming, et autres
Publié: (2025)

Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity
par: Zuo, Shiyuan, et autres
Publié: (2024)

RITA: Automatic Framework for Designing of Resilient IoT Applications
par: Pessoa, Luis Eduardo, et autres
Publié: (2024)

WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols
par: Maheri, Mohammad M, et autres
Publié: (2025)

Flatness-aware Sequential Learning Generates Resilient Backdoors
par: Pham, Hoang, et autres
Publié: (2024)

Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines
par: Ahad, Tanzim, et autres
Publié: (2026)

Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
par: Fang, Junyuan, et autres
Publié: (2025)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
par: Srivastava, Saksham Sahai, et autres
Publié: (2025)

How Catastrophic is Your LLM? Certifying Risk in Conversation
par: Wang, Chengxiao, et autres
Publié: (2025)

FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in FL
par: Hallaji, Ehsan, et autres
Publié: (2025)

OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
par: Wang, Kaixiang, et autres
Publié: (2026)

Research on Key Technologies for Cross-Cloud Federated Training of Large Language Models
par: Yang, Haowei, et autres
Publié: (2024)

FHE-Agent: Automating CKKS Configuration for Practical Encrypted Inference via an LLM-Guided Agentic Framework
par: Xu, Nuo, et autres
Publié: (2025)

Hierarchical Adversarially-Resilient Multi-Agent Reinforcement Learning for Cyber-Physical Systems Security
par: Alqithami, Saad
Publié: (2025)

Privacy-Preserving in Blockchain-based Federated Learning Systems
par: M., Sameera K., et autres
Publié: (2024)

Oblivious Defense in ML Models: Backdoor Removal without Detection
par: Goldwasser, Shafi, et autres
Publié: (2024)

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
par: Nie, Yuzhou, et autres
Publié: (2024)

A Note on Non-Composability of Layerwise Approximate Verification for Neural Inference
par: Zamir, Or
Publié: (2026)

Excuse me, sir? Your language model is leaking (information)
par: Zamir, Or
Publié: (2024)

SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents
par: Masoor, Hari
Publié: (2025)

Learning Communication Between Heterogeneous Agents in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence
par: Popa, Alex, et autres
Publié: (2026)