Cover Image

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nakamura, Mason, Kumar, Abhinav, Mahmud, Saaduddin, Abdelnabi, Sahar, Zilberstein, Shlomo, Bagdasarian, Eugene
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Cryptography and Security I.2.7; I.2.11
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
by: Pulipaka, Sidharth, et al.
Published: (2026)

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

Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
by: Li, Weijun, et al.
Published: (2024)

Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models
by: Nakamura, Mason, et al.
Published: (2025)

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults
by: Usman, Rana Muhammad
Published: (2026)

Research on Security Enhancement Methods for Adversarial Robust Large Language Model Intelligent Agents for Medical Decision-Making Tasks
by: Hu, Saisai
Published: (2026)

Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
by: Ge, Yuxu
Published: (2026)

Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
by: Ravindran, Santhosh Kumar
Published: (2026)

Security Considerations for Multi-agent Systems
by: Nguyen, Tam, et al.
Published: (2026)

Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP Agents
by: Shehab, Mohammed A.
Published: (2025)

FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning
by: Zhang, Su, et al.
Published: (2026)

LLM Scalability Risk for Agentic-AI and Model Supply Chain Security
by: Ahi, Kiarash, et al.
Published: (2026)

Latent Cache Flow: Model-to-Model Communication Without Text
by: Rossi, Maximillian, et al.
Published: (2026)

Secure Decentralized Learning with Blockchain
by: Zhang, Xiaoxue, et al.
Published: (2023)

Memory poisoning and secure multi-agent systems
by: Torra, Vicenç, et al.
Published: (2026)

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

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
by: Garov, Kostadin, et al.
Published: (2023)

VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs
by: Gu, Zixuan, et al.
Published: (2025)

Evaluating Membership Inference Attacks in heterogeneous-data setups
by: van Dartel, Bram, et al.
Published: (2025)

Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
by: Ray, Aninda
Published: (2026)

Sovereign-OS: A Charter-Governed Operating System for Autonomous AI Agents with Verifiable Fiscal Discipline
by: Yuan, Aojie, et al.
Published: (2026)

Applying Cognitive Design Patterns to General LLM Agents
by: Wray, Robert E., et al.
Published: (2025)

Owner-Harm: A Missing Threat Model for AI Agent Safety
by: Zhang, Dongcheng, et al.
Published: (2026)

MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
by: Sidik, Bronislav, et al.
Published: (2026)

ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
by: Chang, Jiale, et al.
Published: (2026)

PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation
by: Wang, Yuchen, et al.
Published: (2026)

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
by: Wang, Zixu, et al.
Published: (2026)

FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
by: Fan, Flint Xiaofeng, et al.
Published: (2024)

PRIMA: Operational Patterns for Resilient Multi-Agent Research with Verifiable Identity and Convergent Feedback
by: Annapureddy, Sasank
Published: (2026)

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
by: Costa, Rimom
Published: (2025)

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

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study
by: Xu, Luyao, et al.
Published: (2026)

Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
by: Wang, Xiaohua, et al.
Published: (2026)

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

From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agents
by: Petrova, Tatiana, et al.
Published: (2025)

Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay
by: Wang, Xiaohua, et al.
Published: (2026)

Post Hoc Extraction of Pareto Fronts for Continuous Control
by: Thakar, Raghav, et al.
Published: (2026)

Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews
by: Li, Bowen, et al.
Published: (2026)

Towards Optimal Agentic Architectures for Offensive Security Tasks
by: David, Isaac, et al.
Published: (2026)

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