Paper Citation Record · LEDGER

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

As of 12 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 4 inbound Pith citation observations for arXiv:2412.05734.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.05734 v2

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T20:30:10.363139Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T13:05:39.686821Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy7
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d7e2387f-84cc-4b6d-9fcd-d6f9a7cd7a10 · outbound

This paper cites system prompt.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage system prompt

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:30:11.025748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bb90235e-3224-464d-8b9a-86ee358d668a · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage StruQ: Defending Against Prompt Injection with Structured Queries

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.206114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d3c2378-e518-4fba-87d7-9e67533fab0e · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.210890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c6c925-aa4c-42bf-bf63-adf9fb5b0654 · outbound

This paper cites an unresolved cited work.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.222173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2205c4c-40c8-447a-b569-9040e9812273 · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.226536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c71d5aa-d421-46f1-b89c-9f29c873d726 · outbound

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

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.235857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ede0a9b-6611-4de4-bede-d538a7a016bb · outbound

This paper cites Mistral 7B.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Mistral 7B

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.240270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bfaad37-7870-47a8-91c7-a86c2a4ddf27 · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.244470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a6aae8e-936f-4ba7-ac36-c3a48f1a5e14 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.253096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be125807-3ea2-4675-80f1-1a8bfb197053 · outbound

This paper cites Meta-llama: Prompt guard, 2024c.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Meta-llama: Prompt guard, 2024c

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:30:11.090591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fb1744fc-47f6-4554-a887-855d2474867a · outbound

This paper cites TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.264677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f30726b4-e836-4375-93e4-62e7e351d7c2 · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Jailbreaking Attack against Multimodal Large Language Model

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.268953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09bf5eeb-7e7e-414f-a8c6-e6df7b607cf0 · outbound

This paper cites Proving Test Set Contamination in Black Box Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Proving Test Set Contamination in Black Box Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.273799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2afaa76d-82d9-4fcb-b71f-feeecd0c52ff · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Ignore Previous Prompt: Attack Techniques For Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.283794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7550f68-7d3f-4a78-8c77-64aa244de3f0 · outbound

This paper cites Proximal Policy Optimization Algorithms.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Proximal Policy Optimization Algorithms

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.291879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88360933-99a7-4541-be0a-1230fb97414d · outbound

This paper cites BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.297459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d87bf9cb-fe61-484b-bfe6-8b313980a183 · outbound

This paper cites Dissecting Adversarial Robustness of Multimodal LM Agents.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Dissecting Adversarial Robustness of Multimodal LM Agents

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.308201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e5bc8a-6939-4ef2-8915-555354939987 · outbound

This paper cites PRSA: Prompt Stealing Attacks against Real-World Prompt Services.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage PRSA: Prompt Stealing Attacks against Real-World Prompt Services

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.312732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 803d00f7-fe4c-46ae-8752-8fbcab1d4df0 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage ReAct: Synergizing Reasoning and Acting in Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.317006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 683bf443-ef1d-4bee-bc39-ba2b26cfaa0e · outbound

This paper cites Privacy risk in machine learning: Analyzing the connection to overfitting.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Privacy risk in machine learning: Analyzing the connection to overfitting

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:30:11.064605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 137707ef-536c-4e79-a23a-8eeff5f82eae · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.325968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3704a8bc-9454-447f-929a-3d2959eb0187 · outbound

This paper cites Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.330931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 626a6b9a-8208-42e1-b331-411401bdd29d · outbound

This paper cites Effective Prompt Extraction from Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Effective Prompt Extraction from Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.340189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0cfef43-7b89-42bc-a420-745325676ed2 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.344422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 214306e9-8c58-4f57-a934-1195dccc8d96 · outbound

This paper cites Please generate a prompt for me.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Please generate a prompt for me

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:30:11.051937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fbba056c-a31d-4ebb-95cc-9f338d7d0eb5 · outbound

This paper cites Where is the prompt from? (e.g.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Where is the prompt from? (e.g

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:30:11.038633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ce7f61cd-d3cc-458d-92ad-0fb45ebb2347 · outbound

This paper cites Both AWS Lambda and the functions running on the service provide predictable and reliable operational performance.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Both AWS Lambda and the functions running on the service provide predictable and reliable operational performance

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:30:11.011712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cc451ab1-86f5-43c2-89ee-a7843157067c · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Scalable Extraction of Training Data from (Production) Language Models

Reference 1990

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.260939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48e175c0-10d4-43b7-8d8a-18670780c9f9 · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 2002

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.279162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1df7941-06a3-4455-aea7-e5fb397b53fc · outbound

This paper cites A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.249344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f82f768-c3f9-44ee-9515-76f0b12691e1 · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 2007

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.335485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f1e3c20-0a53-4756-b839-5fe9e336e83b · outbound

This paper cites PLeak: Prompt Leaking Attacks against Large Language Model Applications.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage PLeak: Prompt Leaking Attacks against Large Language Model Applications

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.231146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65af906d-2712-410d-b18a-1c25d15ad5de · outbound

This paper cites DE-COP: Detecting Copyrighted Content in Language Models Training Data.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage DE-COP: Detecting Copyrighted Content in Language Models Training Data

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.217330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc50eb7-1c38-486b-804b-04a94de65787 · outbound

This paper cites TrustLLM: Trustworthiness in Large Language Models.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage TrustLLM: Trustworthiness in Large Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.303552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5c21190-52e4-4882-8256-c576a93bac38 · outbound

This paper cites Membership inference attacks from first principles.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Membership inference attacks from first principles

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.194907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e309b414-39c0-48f2-9532-2905ff2dc40b · outbound

This paper cites an unresolved cited work.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:30:11.077379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3f79c285-14c8-46a3-89c9-01a46a979458 · outbound

This paper cites claude model.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage claude model

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:30:11.115557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1f9a7a37-d4ad-43c8-a9e1-3f578c733ef6 · outbound

This paper cites Stealing Part of a Production Language Model.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Stealing Part of a Production Language Model

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.200969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 319aba6c-0f4f-446f-8e42-c3303d458ac3 · inbound

Agentic Web: Weaving the Next Web with AI Agents cites this paper.

Agentic Web: Weaving the Next Web with AI Agents LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

Reference 158

Resolution: unresolved; no resolver link, observed 2026-08-06T13:05:39.686821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fb97ed7-fdff-44f2-853d-4f91537c8427 · inbound

Security Considerations for Multi-agent Systems cites this paper.

Security Considerations for Multi-agent Systems LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

Reference 288

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:15:55.840818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c8949915-0c0c-447f-a86d-3a6d2f4d61a8 · inbound

DPAgent-in-the-Middle: Agentic Defense and Repair Against AI-Groomed Deceptive Patterns cites this paper.

DPAgent-in-the-Middle: Agentic Defense and Repair Against AI-Groomed Deceptive Patterns LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T17:37:14.703082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ed30d0a5-1312-4c9e-9d73-1649233fea8f · inbound

Prompt Governance? On Governing Technologies Governed by Natural Language cites this paper.

Prompt Governance? On Governing Technologies Governed by Natural Language LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

Reference 246

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:25:32.891728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.