Rethinking Agent Security as a Networking Problem | Paper Citation Record

Observation 307f55f9-9df6-44ed-9392-4dd75055892e · outbound

This paper cites Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution.

Rethinking Agent Security as a Networking Problem Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.303564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75af99fd-35b9-45be-bb0e-539c3b19fb0a · outbound

This paper cites Model context protocol.

Rethinking Agent Security as a Networking Problem Model context protocol

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.138420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7bc4a230-bca9-4d4e-90b1-0e0bda6b742d · outbound

This paper cites Air- GapAgent: Protecting privacy-conscious conversational agents.

Rethinking Agent Security as a Networking Problem Air- GapAgent: Protecting privacy-conscious conversational agents

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.123389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 085a062e-7873-4d4d-87bf-6f2a28a46938 · outbound

This paper cites Off by default! InProceedings of the 4th ACM Workshop on Hot Topics in Networks (HotNets-IV), College Park, MD, 2005.

Rethinking Agent Security as a Networking Problem Off by default! InProceedings of the 4th ACM Workshop on Hot Topics in Networks (HotNets-IV), College Park, MD, 2005

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.098945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ac23da05-14a3-4f9e-ba6b-6351207f1f80 · outbound

This paper cites Freedman, Justin Pettit, Jianying Luo, Nick McKeown, and Scott Shenker.

Rethinking Agent Security as a Networking Problem Freedman, Justin Pettit, Jianying Luo, Nick McKeown, and Scott Shenker

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.083703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9742d581-a98e-4778-9ff6-d7453dbaab05 · outbound

This paper cites Freedman, Dan Boneh, Nick McKeown, and Scott Shenker.

Rethinking Agent Security as a Networking Problem Freedman, Dan Boneh, Nick McKeown, and Scott Shenker

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.069453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 22ba1fa3-3d01-42f6-a726-dacd082a736b · outbound

This paper cites {StruQ}: Defending against prompt injection with structured queries.

Rethinking Agent Security as a Networking Problem {StruQ}: Defending against prompt injection with structured queries

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.054036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0fb0ed77-c5b1-4fcf-97e5-3e97c8b89892 · outbound

This paper cites Secalign: Defending against prompt injection with preference optimization.

Rethinking Agent Security as a Networking Problem Secalign: Defending against prompt injection with preference optimization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.344313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0334ae0a-09da-44dc-9871-32a9fb6b030c · outbound

This paper cites Agentpoison: Red-teaming llm agents via poisoning memory or knowl- edge bases.Advances in Neural Information Processing Systems, 37:130185–130213, 2024.

Rethinking Agent Security as a Networking Problem Agentpoison: Red-teaming llm agents via poisoning memory or knowl- edge bases.Advances in Neural Information Processing Systems, 37:130185–130213, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.348775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b36724f7-1f7b-4d93-9381-ed66a003bfb7 · outbound

This paper cites Overprivileged by design: AI agents as cloud escalation vectors.

Rethinking Agent Security as a Networking Problem Overprivileged by design: AI agents as cloud escalation vectors

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.020107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 10c52286-c590-4493-99a8-3e7a23025f32 · outbound

This paper cites Securing AI Agents with Information-Flow Control.

Rethinking Agent Security as a Networking Problem Securing AI Agents with Information-Flow Control

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.357689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d423be8-c845-4d2b-ad13-3306bed23c1e · outbound

This paper cites Defeating Prompt Injections by Design.

Rethinking Agent Security as a Networking Problem Defeating Prompt Injections by Design

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.362927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a09a59c-fecb-44a5-a867-1443ac50449a · outbound

This paper cites AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents.

Rethinking Agent Security as a Networking Problem AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:54.005425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5d732177-794b-4a5f-a7fe-332b5dd6d2f2 · outbound

This paper cites Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 57(7):1–36, 2025.

Rethinking Agent Security as a Networking Problem Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 57(7):1–36, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.372005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14a28adc-8e32-4b04-8a6f-ca792ee3b9cc · outbound

This paper cites an unresolved cited work.

Rethinking Agent Security as a Networking Problem Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:16:53.980500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation abdb78e1-07bf-4c0c-ad3f-540f869ee3ae · outbound

This paper cites Memory injection attacks on llm agents via query-only interaction.Advances in Neural Information Processing Systems, 38:46697–46731, 2026.

Rethinking Agent Security as a Networking Problem Memory injection attacks on llm agents via query-only interaction.Advances in Neural Information Processing Systems, 38:46697–46731, 2026

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.965986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation afa7f544-284d-42f7-80a1-682cc86e9981 · outbound

This paper cites Towards verifiably safe tool use for llm agents.

Rethinking Agent Security as a Networking Problem Towards verifiably safe tool use for llm agents

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.952047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a96d1fef-c4fd-498d-b08e-444032087434 · outbound

This paper cites AgentLeak: A full-stack benchmark for privacy leakage in multi-agent LLM systems.arXiv preprint arXiv:2602.11510, February 2026.

Rethinking Agent Security as a Networking Problem AgentLeak: A full-stack benchmark for privacy leakage in multi-agent LLM systems.arXiv preprint arXiv:2602.11510, February 2026

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.389986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c471bd-da43-4778-987e-87ab27143bc4 · outbound

This paper cites Wasp: Benchmarking web agent security against prompt injection attacks.Advances in Neural Information Processing Systems, 38, 2026.

Rethinking Agent Security as a Networking Problem Wasp: Benchmarking web agent security against prompt injection attacks.Advances in Neural Information Processing Systems, 38, 2026

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.937836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bd14a932-ea5c-4abf-beac-791911997f00 · outbound

This paper cites AI agents are the biggest data security threat you’re not governing.

Rethinking Agent Security as a Networking Problem AI agents are the biggest data security threat you’re not governing

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.922661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 805acb9c-2d57-4b25-8f79-b61dc624336f · outbound

This paper cites Agent2agent (A2A) protocol.

Rethinking Agent Security as a Networking Problem Agent2agent (A2A) protocol

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.907836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3274f44a-94e6-4713-bd52-2347f864e27d · outbound

This paper cites Not what you’ve signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection.

Rethinking Agent Security as a Networking Problem Not what you’ve signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.892852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 14e2ac38-18e9-4ab8-a80b-8296a1587c9a · outbound

This paper cites Bypassing LLM guardrails: An empirical analysis of eva- sion attacks against prompt injection and jailbreak detection systems, 2025.

Rethinking Agent Security as a Networking Problem Bypassing LLM guardrails: An empirical analysis of eva- sion attacks against prompt injection and jailbreak detection systems, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.878294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 096b3df7-3605-4b26-9a17-35957152ba5c · outbound

This paper cites The OAuth 2.0 authorization framework.

Rethinking Agent Security as a Networking Problem The OAuth 2.0 authorization framework

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.864145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 42e92a12-2d7e-4a9f-9608-4b5405e86323 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Rethinking Agent Security as a Networking Problem Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.422410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad8ee4e6-8e34-41c1-9042-17c252d61947 · outbound

This paper cites Break- ing and fixing defenses against control-flow hijacking in multi-agent systems.arXiv preprint arXiv:2510.17276, 2025.

Rethinking Agent Security as a Networking Problem Break- ing and fixing defenses against control-flow hijacking in multi-agent systems.arXiv preprint arXiv:2510.17276, 2025

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.426857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e52efd2-8208-4a1e-921e-7b31bea700d2 · outbound

This paper cites The task shield: Enforcing task alignment to defend against indirect prompt injection in LLM agents.

Rethinking Agent Security as a Networking Problem The task shield: Enforcing task alignment to defend against indirect prompt injection in LLM agents

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.846847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 304440f1-a086-4495-a037-cd6867237972 · outbound

This paper cites A Critical Evaluation of Defenses against Prompt Injection Attacks.

Rethinking Agent Security as a Networking Problem A Critical Evaluation of Defenses against Prompt Injection Attacks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.434773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fa22a94-faa1-4e26-89f4-769eb59c2aef · outbound

This paper cites When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents.

Rethinking Agent Security as a Networking Problem When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.438925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9f6ab40-a906-4dc3-bcbc-96f77a87229d · outbound

This paper cites Frans Kaashoek, Eddie Kohler, and Robert Morris.

Rethinking Agent Security as a Networking Problem Frans Kaashoek, Eddie Kohler, and Robert Morris

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.831339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bbbe41cc-bd09-411d-bdb0-31dba52f50a1 · outbound

This paper cites Lakera guard.

Rethinking Agent Security as a Networking Problem Lakera guard

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.816326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 278e6b90-2561-48ca-80ea-0f884286fc83 · outbound

This paper cites Inan, Sahar Abdelnabi, Janardhan Kulka- rni, Lukas Wutschitz, Reza Shokri, Christopher G.

Rethinking Agent Security as a Networking Problem Inan, Sahar Abdelnabi, Janardhan Kulka- rni, Lukas Wutschitz, Reza Shokri, Christopher G

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.800917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c532226d-88ca-4992-b06f-1d85fee1064c · outbound

This paper cites Improving google a2a protocol: Protecting sensitive data and mitigating unintended harms in multi-agent systems.ACM Transactions on Software Engineering and Methodology, 2025.

Rethinking Agent Security as a Networking Problem Improving google a2a protocol: Protecting sensitive data and mitigating unintended harms in multi-agent systems.ACM Transactions on Software Engineering and Methodology, 2025

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.785731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e45143a1-69f0-49d0-871a-87ea66245a92 · outbound

This paper cites ClawLess: A Security Model of AI Agents.

Rethinking Agent Security as a Networking Problem ClawLess: A Security Model of AI Agents

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.461950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 090b13fd-312f-4d4d-83f9-4f61e491471e · outbound

This paper cites Agentauditor: Human-level safety and security evaluation for llm agents.Advances in Neural Information Processing Systems, 38:43241–43298, 2026.

Rethinking Agent Security as a Networking Problem Agentauditor: Human-level safety and security evaluation for llm agents.Advances in Neural Information Processing Systems, 38:43241–43298, 2026

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.466663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 442b940f-952c-4a86-a9d5-1b2a443258f3 · outbound

This paper cites A holistic approach to undesired content detection in the real world.Proceedings of the AAAI Conference on Artificial Intelligence, 37(12):15009–15018, 2023.

Rethinking Agent Security as a Networking Problem A holistic approach to undesired content detection in the real world.Proceedings of the AAAI Conference on Artificial Intelligence, 37(12):15009–15018, 2023

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.759446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2f405ee0-9e96-42d5-97a8-4e2301388037 · outbound

This paper cites Same model, different hat.

Rethinking Agent Security as a Networking Problem Same model, different hat

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.744203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cc114753-dc35-4cc2-8ee8-5baf3c84c28f · outbound

This paper cites cell- mate: Sandboxing browser ai agents.arXiv preprint arXiv:2512.12594, 2025.

Rethinking Agent Security as a Networking Problem cell- mate: Sandboxing browser ai agents.arXiv preprint arXiv:2512.12594, 2025

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.480555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 131827f3-1758-499a-9774-f03e7d663a3d · outbound

This paper cites Veriguard: Enhancing llm agent safety via verified code generation.arXiv preprint arXiv:2510.05156, 2025.

Rethinking Agent Security as a Networking Problem Veriguard: Enhancing llm agent safety via verified code generation.arXiv preprint arXiv:2510.05156, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.485071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50dfe044-bab5-4465-88c6-05ce4b5a19bb · outbound

This paper cites Can LLMs keep a secret? Testing privacy implications of language models via contextual in- tegrity theory.

Rethinking Agent Security as a Networking Problem Can LLMs keep a secret? Testing privacy implications of language models via contextual in- tegrity theory

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.728575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9b6b5d19-4a5b-4f10-ac96-cdcf9726ff52 · outbound

This paper cites Myers and Barbara Liskov.

Rethinking Agent Security as a Networking Problem Myers and Barbara Liskov

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.713491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 069a84aa-156b-461f-81c9-a4922b5f4b3b · outbound

This paper cites Omni-leak: Orchestrator multi-agent net- work induced data leakage.arXiv preprint arXiv:2602.13477, 2026.

Rethinking Agent Security as a Networking Problem Omni-leak: Orchestrator multi-agent net- work induced data leakage.arXiv preprint arXiv:2602.13477, 2026

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.499684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5511faee-4228-44ad-9675-d5451e996a66 · outbound

This paper cites Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents.

Rethinking Agent Security as a Networking Problem Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.504149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ce2dff6-41c4-42ae-98b4-c42a38b1fe79 · outbound

This paper cites Privacy as contextual integrity.Washington Law Review, 79(1):119–157, 2004.

Rethinking Agent Security as a Networking Problem Privacy as contextual integrity.Washington Law Review, 79(1):119–157, 2004

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.699595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4a089823-b7eb-4048-963d-ad3800069634 · outbound

This paper cites Why traditional security fails in the age of non- deterministic AI.

Rethinking Agent Security as a Networking Problem Why traditional security fails in the age of non- deterministic AI

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.685891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3d25ab42-31cf-458e-94d5-2162e3228003 · outbound

This paper cites Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents.

Rethinking Agent Security as a Networking Problem Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.518336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ab5920f-18cb-49f4-b5b9-91884042d05a · outbound

This paper cites Agentbay: A hybrid interaction sandbox for seamless human-ai intervention in agentic systems.arXiv preprint arXiv:2512.04367, 2025.

Rethinking Agent Security as a Networking Problem Agentbay: A hybrid interaction sandbox for seamless human-ai intervention in agentic systems.arXiv preprint arXiv:2512.04367, 2025

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.523086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921df08d-5ba6-4670-a5c6-4363430229fb · outbound

This paper cites Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks.

Rethinking Agent Security as a Networking Problem Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.527562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b87b12c-7b12-4222-bb91-42439fdce24d · outbound

This paper cites NeMo guardrails: A toolkit for controllable and safe LLM applications with programmable rails.

Rethinking Agent Security as a Networking Problem NeMo guardrails: A toolkit for controllable and safe LLM applications with programmable rails

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.672607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b8655260-9447-4835-b15f-934814a0e315 · outbound

This paper cites Zero trust architecture.

Rethinking Agent Security as a Networking Problem Zero trust architecture

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.657947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c3cf9970-a376-4692-9cd8-1ea295bc4162 · outbound

This paper cites Saltzer, David P.

Rethinking Agent Security as a Networking Problem Saltzer, David P

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.641760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 38eed1c4-1e1e-456b-a39e-017d6868533b · outbound

This paper cites Saltzer and Michael D.

Rethinking Agent Security as a Networking Problem Saltzer and Michael D

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.625403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e940e040-cba9-4421-9736-6850d2a20f13 · outbound

This paper cites Sandhu, Edward J.

Rethinking Agent Security as a Networking Problem Sandhu, Edward J

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.610001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7a57f245-ebd7-4ee6-8e9c-2307eb25f17a · outbound

This paper cites Pri- vacyLens: Evaluating privacy norm awareness of language models in action.

Rethinking Agent Security as a Networking Problem Pri- vacyLens: Evaluating privacy norm awareness of language models in action

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.594727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e7da0d6e-0a99-42be-9729-2f18aa7f6977 · outbound

This paper cites Rollback-recovery for middleboxes.

Rethinking Agent Security as a Networking Problem Rollback-recovery for middleboxes

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.578873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a2d74c86-6d82-4e25-9cc5-cfb8197de3e3 · outbound

This paper cites Making middleboxes someone else’s problem: Network processing as a cloud service.

Rethinking Agent Security as a Networking Problem Making middleboxes someone else’s problem: Network processing as a cloud service

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.563237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 35ffd793-4f73-4ec1-9e49-f064a3a4a900 · outbound

This paper cites BlindBox: Deep packet inspection over encrypted traffic.

Rethinking Agent Security as a Networking Problem BlindBox: Deep packet inspection over encrypted traffic

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.546824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4ee59f58-654d-4619-8d57-9397e3a25186 · outbound

This paper cites Progent: Programmable privilege control for llm agents.arXiv e-prints, pages arXiv–2504, 2025.

Rethinking Agent Security as a Networking Problem Progent: Programmable privilege control for llm agents.arXiv e-prints, pages arXiv–2504, 2025

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.530999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2174ba0f-82f6-4ec8-af11-665a1b2323b0 · outbound

This paper cites From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors.

Rethinking Agent Security as a Networking Problem From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.575056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bddfdab1-8b69-45c3-a993-89ccd1560a7f · outbound

This paper cites AI agents are becoming authorization bypass paths.

Rethinking Agent Security as a Networking Problem AI agents are becoming authorization bypass paths

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.513775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 798cea79-2e4d-4e8e-ba7b-28b3843d9506 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Rethinking Agent Security as a Networking Problem The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.583963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cbe6a92-cb31-4c05-874e-93726b8777f5 · outbound

This paper cites Privacy in action: Towards realistic privacy mitigation and evaluation for LLM-powered agents.

Rethinking Agent Security as a Networking Problem Privacy in action: Towards realistic privacy mitigation and evaluation for LLM-powered agents

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.498000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 81453714-72fd-42b8-b3fc-6b302b4f9afc · outbound

This paper cites Sok: Evaluating jailbreak guardrails for large language models.

Rethinking Agent Security as a Networking Problem Sok: Evaluating jailbreak guardrails for large language models

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.482391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 55a336a1-8651-4753-8173-270eafd5b5e7 · outbound

This paper cites IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems.

Rethinking Agent Security as a Networking Problem IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.597372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74e8b5f8-adc1-4ee6-b059-2ff98c63d02e · outbound

This paper cites GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning.

Rethinking Agent Security as a Networking Problem GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.602071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a45c84b-e8d1-4c47-81fc-feee9fb2654b · outbound

This paper cites SIFF: A stateless internet flow filter to mitigate DDoS flooding attacks.

Rethinking Agent Security as a Networking Problem SIFF: A stateless internet flow filter to mitigate DDoS flooding attacks

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.466718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c3312728-17f5-4e05-8cba-74ada3c8feb5 · outbound

This paper cites A DoS- limiting network architecture.

Rethinking Agent Security as a Networking Problem A DoS- limiting network architecture

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.450831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b02123c1-dbfb-497b-a416-dee577e8c4a3 · outbound

This paper cites ReAct: Synergizing reasoning and acting in language models.

Rethinking Agent Security as a Networking Problem ReAct: Synergizing reasoning and acting in language models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.616158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d749151e-5914-4f48-8875-690664504b3c · outbound

This paper cites Temporal dynamics of mem- ory poisoning in web3-style llm agents.IEEE Access, 2026.

Rethinking Agent Security as a Networking Problem Temporal dynamics of mem- ory poisoning in web3-style llm agents.IEEE Access, 2026

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.425044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 524731c4-3e4c-4b1a-bd71-5b83f9c00d9c · outbound

This paper cites Making information flow explicit in HiStar.

Rethinking Agent Security as a Networking Problem Making information flow explicit in HiStar

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.409351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 26f6f9af-a124-467e-b693-d47653751744 · outbound

This paper cites Injecagent: Benchmarking indirect prompt injections in tool-integrated large lan- guage model agents.

Rethinking Agent Security as a Networking Problem Injecagent: Benchmarking indirect prompt injections in tool-integrated large lan- guage model agents

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.629850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9121ddc-0084-4c58-b0a5-a12b43efabfc · outbound

This paper cites Towards Action Hijacking of Large Language Model-based Agent.

Rethinking Agent Security as a Networking Problem Towards Action Hijacking of Large Language Model-based Agent

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.634434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe36e78b-b5bf-4996-8d88-d11f94fc0f72 · outbound

This paper cites AgentDAM: Privacy leakage evaluation for autonomous web agents.

Rethinking Agent Security as a Networking Problem AgentDAM: Privacy leakage evaluation for autonomous web agents

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.382866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8e10ec44-80f8-4ff2-94f6-1c098895bc68 · outbound

This paper cites RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage.

Rethinking Agent Security as a Networking Problem RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.643873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a11e147c-8315-4aff-9114-684a09cfc24b · outbound

This paper cites Rescriber: Smaller- LLM-powered user-led data minimization for LLM-based chatbots.

Rethinking Agent Security as a Networking Problem Rescriber: Smaller- LLM-powered user-led data minimization for LLM-based chatbots

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:16:53.363098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 97d3c3fa-887f-4d8e-bf85-d9d2c3c98277 · outbound

This paper cites CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities.

Rethinking Agent Security as a Networking Problem CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.653903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51282d5b-1aa8-4e13-afdd-045001046885 · outbound

This paper cites an unresolved cited work.

Rethinking Agent Security as a Networking Problem Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.318565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers