Paper Citation Record · LEDGER

SecAlign: Defending Against Prompt Injection with Preference Optimization

As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 34 inbound Pith citation observations for arXiv:2410.05451.

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

pith.paper-citation-record.v1
2410.05451 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 34 of 34 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:38:39.301351Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T23:36:22.936259Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 6156e6c5-567b-4b99-ba90-e62cfeaae84c · inbound

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models cites this paper.

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T10:32:28.233502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0db6692-c76b-48b3-b8b8-14609638632d · inbound

A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense cites this paper.

A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T22:53:20.639962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dae070a-56be-4e5f-b63a-539284747a04 · inbound

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents cites this paper.

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T20:06:58.233116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c818245-27f2-4528-a0c2-76a337aeccac · inbound

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety cites this paper.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 141

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.779160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2a9cecac-da47-40d9-aa64-005a1ff22a92 · inbound

Prompt Injection Attack to Tool Selection in LLM Agents cites this paper.

Prompt Injection Attack to Tool Selection in LLM Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:08:29.020566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 454aa68a-fc7b-4753-ad8b-702f8ba5fbfc · inbound

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction cites this paper.

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-22T19:11:58.012323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4563f920-b373-4c37-897a-d4a746f7db47 · inbound

ACE: A Security Architecture for LLM-Integrated App Systems cites this paper.

ACE: A Security Architecture for LLM-Integrated App Systems SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-22T18:06:54.286509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e7c1170b-fa30-47c5-8ca8-36d4fe4c9503 · inbound

OET: Optimization-based prompt injection Evaluation Toolkit cites this paper.

OET: Optimization-based prompt injection Evaluation Toolkit SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T04:38:39.301351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd3fd14-a348-4069-957d-a83be6e5f729 · inbound

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs cites this paper.

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T23:23:38.685456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92a5095f-584a-4555-8586-88a61d03c25b · inbound

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

A Critical Evaluation of Defenses against Prompt Injection Attacks SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:36:09.746380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09fdaad2-4160-442b-b84e-2d0dc3a1298b · inbound

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

Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:59:22.064371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ede77e6-208c-4571-8ddc-ee3fe5407b0c · inbound

Defending Against Prompt Injection With a Few DefensiveTokens cites this paper.

Defending Against Prompt Injection With a Few DefensiveTokens SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:38.828080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b79bbf34-94e8-487c-bfad-835511aa37cf · inbound

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents cites this paper.

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-19T04:12:02.170806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 16634dc5-cecf-4163-a0d7-286a5723c790 · inbound

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain cites this paper.

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T10:44:10.399166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 555e7fec-8fa6-4ac4-badd-e5a12015c9d3 · inbound

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation cites this paper.

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T21:33:57.102424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c262896-4410-4d02-9c69-4315c92d971e · inbound

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents cites this paper.

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T08:06:09.522680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcc30560-0954-4523-9158-2be89eac7dd3 · inbound

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 180

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:42:21.914241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 35d43ed6-4797-4df0-b6b8-c14e88ab66be · inbound

Toward a Safe Internet of Agents cites this paper.

Toward a Safe Internet of Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-17T03:18:56.885802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 566d8f0b-9332-4c18-8dac-7c8b7a4f5eaa · inbound

AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness Against Large Language Models cites this paper.

AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness Against Large Language Models SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T12:52:49.101462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfa1f9af-83a5-4e2b-a4c6-6d8c334b1dd6 · inbound

Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory cites this paper.

Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:36:10.585625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 377c23ef-e515-45a9-9e0c-cbc3f560a1f6 · inbound

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills cites this paper.

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:46:17.200381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation af047c79-62ae-43c9-ba05-b18cbbb12463 · inbound

A Sentence Relation-Based Approach to Sanitizing Malicious Instructions cites this paper.

A Sentence Relation-Based Approach to Sanitizing Malicious Instructions SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:06:43.365091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2d6c8c29-bc32-4478-96af-0c0e02594d39 · inbound

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection cites this paper.

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:47:21.337632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 90beb3a0-1e9f-4bf0-bfe7-3894b5c18d73 · inbound

Web Agents Should Adopt the Plan-Then-Execute Paradigm cites this paper.

Web Agents Should Adopt the Plan-Then-Execute Paradigm SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:43:33.387927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 23b62fb7-766d-4375-b67c-6e2f96052aec · inbound

What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents cites this paper.

What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:36:22.938900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b0e91c8f-a793-4727-826e-d19e4a2f315b · inbound

Agent Safety Is Action Alignment cites this paper.

Agent Safety Is Action Alignment SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T09:54:34.990454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 99b5583a-a398-4e35-9086-452c7455a7c7 · inbound

Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents cites this paper.

Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:44:41.472646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 17fc53ab-c396-4b37-a67a-11cde6e242d2 · inbound

Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation cites this paper.

Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T11:28:37.338330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e004625-42f8-46f4-ada6-d0988f2534ca · inbound

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents cites this paper.

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T23:24:19.513672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b9fdc99-be04-4fb2-98ee-3af458b5eefb · inbound

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection cites this paper.

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:37.929904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3623add-4284-47d0-8bfa-52234f36fd50 · inbound

When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems cites this paper.

When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T10:29:59.061970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669dca24-3b73-4494-9bb7-73974c2fc073 · inbound

When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems cites this paper.

When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T04:29:49.865067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5f3f421-b485-4e17-bab6-46092d2d418e · inbound

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models cites this paper.

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T14:21:41.862200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a59a9ec2-571e-4052-9299-c54acff204a3 · inbound

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents cites this paper.

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents SecAlign: Defending Against Prompt Injection with Preference Optimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T19:23:23.073914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.