Reachability, Not Observation: Containing Systems Whose Wiring Changes

arXiv:2609.19720 · cs.CR, cs.NI · Submitted 2026-09-17 · Read on arXiv

cs.CR, cs.NI

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: 29 pages, 3 figures, 17 tables. Companion to arXiv:2609.18145. Code and records for every number are included with the submission

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Guidelines for Artificial Intelligence Containment
• Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications
• Defeating Prompt Injections by Design
• Auditing MCP Servers for Over-Privileged Tool Capabilities
• Frontier AI systems have surpassed the self-replicating red line
• Progent: Securing AI Agents with Privilege Control
• Reaching Every Position Without Searching: Rotating Sparse Wiring on the Hypercube as a Substitute for Attention

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs