PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916033203273728 |
|---|---|
| author | Barbieri, Sidnei Ferraz, Ágney Lopes Roth Júnior, Lourenço Alves Pereira |
| author_facet | Barbieri, Sidnei Ferraz, Ágney Lopes Roth Júnior, Lourenço Alves Pereira |
| contents | Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and how failures should be recorded. We present PocketAgents, a manifest-driven library of autonomous defense agents. Each agent is installed as three data files: a manifest, a prompt, and a runtime context. The shared runtime gives the agent bounded telemetry access and accepts only typed reports whose requested action appears in the manifest. We implemented PocketAgents on top of a cyber arena (Perry), a cyber-deception testbed, and evaluated two agents, Command and Control and Exfiltration, in 18 closed-loop trials of a DarkSide-inspired attack on a small enterprise topology. Thirteen trials produced validated network-block actions and contained the attack; four failed schema validation; one produced a valid no-action decision. The experiments show that a typed boundary makes LLM-driven defense measurable, extensible, and attributable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21694 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents Barbieri, Sidnei Ferraz, Ágney Lopes Roth Júnior, Lourenço Alves Pereira Cryptography and Security Artificial Intelligence Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and how failures should be recorded. We present PocketAgents, a manifest-driven library of autonomous defense agents. Each agent is installed as three data files: a manifest, a prompt, and a runtime context. The shared runtime gives the agent bounded telemetry access and accepts only typed reports whose requested action appears in the manifest. We implemented PocketAgents on top of a cyber arena (Perry), a cyber-deception testbed, and evaluated two agents, Command and Control and Exfiltration, in 18 closed-loop trials of a DarkSide-inspired attack on a small enterprise topology. Thirteen trials produced validated network-block actions and contained the attack; four failed schema validation; one produced a valid no-action decision. The experiments show that a typed boundary makes LLM-driven defense measurable, extensible, and attributable. |
| title | PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2605.21694 |