Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T18:32:44.393617Z
Paper Citation Record · LEDGER
Defending Against Prompt Injection With a Few DefensiveTokens
As of 8 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 8 inbound Pith citation observations for arXiv:2507.07974.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-05T15:26:33.475946Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-04T00:59:20.691622Z
Reference resolution
59 of 59 outbound references displayed
- verified exact2
- verified fuzzy5
- unresolved50
- parse uncertain0
- malformed identifier1
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 70deac73-eb39-4506-8e14-af93fb311975 · outbound
This paper cites Get my drift? Catching LLM Task Drift with Activation Deltas.
Defending Against Prompt Injection With a Few DefensiveTokens Get my drift? Catching LLM Task Drift with Activation Deltas
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:38.442495Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2d84767a-0df9-4771-901c-ec6aef9c879b · outbound
This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.
Defending Against Prompt Injection With a Few DefensiveTokens CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:38.557329Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9ab0f8a5-2e4b-41a9-8917-1f35c561db7b · outbound
This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.
Defending Against Prompt Injection With a Few DefensiveTokens StruQ: Defending Against Prompt Injection with Structured Queries
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:38.700951Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ede77e6-208c-4571-8ddc-ee3fe5407b0c · outbound
This paper cites SecAlign: Defending Against Prompt Injection with Preference Optimization.
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 20f911fd-9d68-486c-ba8b-88f71854ef2a · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:38.970617Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f31587f-0f4d-49f9-bcdc-333a23327ed0 · outbound
This paper cites Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael I.
Defending Against Prompt Injection With a Few DefensiveTokens Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael I
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:39.094310Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 994bbd42-cfd1-4ab1-81a0-07436532cf7e · outbound
This paper cites Defeating Prompt Injections by Design.
Defending Against Prompt Injection With a Few DefensiveTokens Defeating Prompt Injections by Design
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:39.188120Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation de3f473a-91df-48b7-b18f-8f49a401832b · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 8
- Resolution
- metadata mismatch
- raw_fallback, observed 2026-08-06T18:32:45.517328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 8a34d255-a3de-41ca-87fb-87e6e020af5d · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:39.601601Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d044c525-6379-4223-bbdb-d62c0e739627 · outbound
This paper cites LoRA: Low-Rank Adaptation of Large Language Models.
Defending Against Prompt Injection With a Few DefensiveTokens LoRA: Low-Rank Adaptation of Large Language Models
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:39.724332Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3b16656-f545-49ea-8283-cec467f7fd34 · outbound
This paper cites Hsu, and Pin-Yu Chen.
Defending Against Prompt Injection With a Few DefensiveTokens Hsu, and Pin-Yu Chen
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:32:50.101732Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c9248236-d609-4c9f-bd72-043c1d0accf3 · outbound
This paper cites Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts.
Defending Against Prompt Injection With a Few DefensiveTokens Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:32:49.825978Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 428da68c-ebbc-4bca-8f4f-fa741a3ee5aa · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 13
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:49.707217Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 355fe044-1d97-405f-9b69-d24229d21e0a · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:40.224826Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b9b7a7aa-011d-4fed-8ba1-a1590d9eedfe · outbound
This paper cites Hashimoto.
Defending Against Prompt Injection With a Few DefensiveTokens Hashimoto
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:32:49.575464Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation d4fc5046-9194-4df1-bf95-869d2c8a54fe · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:49.420803Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 190efc79-74f7-4d83-a635-89f5c2bcb68a · outbound
This paper cites UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models.
Defending Against Prompt Injection With a Few DefensiveTokens UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:40.613792Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 98b6a98b-c918-43b7-83b6-5e56d436e594 · outbound
This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.
Defending Against Prompt Injection With a Few DefensiveTokens Automatic and Universal Prompt Injection Attacks against Large Language Models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:40.695022Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 97f5d211-58eb-4eed-8bc9-2559a5cbf1b7 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:40.780835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 348a0822-5451-4ee3-a4e0-cd7ace13e17c · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:40.944988Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 18e0109c-fb7f-4ce8-851a-86edff0d087d · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:49.145765Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 2003e6b8-6a4b-4646-b29a-455760a2f4d7 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 22
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:49.019498Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7c37b11c-8886-413a-a66a-787f707d5dfc · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 23
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:48.886048Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation feb7ba66-ef8a-4906-9e5c-95035cfd8844 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 24
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:48.768104Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation facda6f5-75d6-452c-a9d7-52b43619f143 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 25
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:48.644595Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 05afec08-e036-489e-8b5e-63d70c2e5a72 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 26
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:48.490841Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 88ad8792-c823-40ff-99cc-0c4d3320fd9f · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 27
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-06T18:32:41.457013Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b56f6ca4-1ac9-4bde-aa6b-6b39ed4d4a73 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:41.570906Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation efbb61b7-605f-4de8-a0ac-9fa53b136c3d · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 29
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:48.360671Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 96e9f6bf-ed86-4970-86bc-a6a86a19c3a0 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:41.740788Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 000820f1-964e-4176-a142-a1133e6a5280 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 31
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:48.092532Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 1da3d644-8260-4e79-bc79-24662ce8a970 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 32
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:47.843438Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c389744f-a32a-419c-a020-dcaa75a4e240 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 33
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:47.615215Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 8afa656f-67a0-4830-852e-bc6aadb1f529 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:42.150644Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f93350a-a74b-442c-979f-f06fbf61e616 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 35
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:47.469220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7e49a9ca-1ddb-4af1-8f21-c4a43cb49d7c · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 36
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:47.299636Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4d236274-ed7b-42ed-88a6-8e8dc36937c9 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 37
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:47.095842Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 867c4399-a773-4c4f-b547-b044dae7e006 · outbound
This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.
Defending Against Prompt Injection With a Few DefensiveTokens The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:42.689401Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f83284f0-90e2-4a1a-ba17-078112756859 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 39
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:46.853657Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c9e12c66-942d-4f13-b196-686c4bf8756d · outbound
This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.
Defending Against Prompt Injection With a Few DefensiveTokens Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:42.838856Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a864402b-0509-43ec-81c8-2df92e7213b2 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 41
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:46.641626Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a5d52f40-3e11-4152-9fb8-299456b639b5 · outbound
This paper cites Effectively Controlling Reasoning Models through Thinking Intervention.
Defending Against Prompt Injection With a Few DefensiveTokens Effectively Controlling Reasoning Models through Thinking Intervention
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:43.052649Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d4a4b962-fc63-4324-a86c-92b825238805 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:46.454818Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4cc98494-dc94-4d14-93b6-57ebe08457f8 · outbound
This paper cites Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment.
Defending Against Prompt Injection With a Few DefensiveTokens Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:43.351303Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44091a2a-b161-497a-9274-e95abd611087 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 45
- Resolution
- verified exact
- raw_fallback, observed 2026-08-06T18:32:44.934779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4300d97a-a3de-4ba7-8848-02d04f2f26a3 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:43.568449Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3b493c9e-0051-4249-a6c6-ed4abde381fe · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 47
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:46.272189Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 801daeeb-141b-498e-8cb4-1a6a8f010be0 · outbound
This paper cites Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy.
Defending Against Prompt Injection With a Few DefensiveTokens Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:43.260092Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 88fb5da2-d55e-4fa5-ab23-6409cdd89dd6 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:43.883708Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cc820dbf-8668-48ed-9fb4-e5843a2f0afc · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 50
- Resolution
- verified exact
- doi, observed 2026-08-06T18:32:44.628903Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c46fd5ac-48fa-416e-9127-e34bc783e919 · outbound
This paper cites On Prompt-Driven Safeguarding for Large Language Models.
Defending Against Prompt Injection With a Few DefensiveTokens On Prompt-Driven Safeguarding for Large Language Models
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:44.096157Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b16a4cff-df7b-45c4-b353-ac8a73dbace6 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 52
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:45.998508Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9a8b2c99-4ef4-43db-a997-d9e4e979a834 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:43.769570Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1426ba8a-b9b4-4876-9c84-1f51bfb9f8b0 · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 54
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:32:45.802563Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation aad169b6-04a0-46ca-8be5-38d353ad6935 · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
Defending Against Prompt Injection With a Few DefensiveTokens Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:44.285307Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6c142056-0b66-43b3-823d-5cbd2bcf3fdf · outbound
This paper cites Gradient Descent.
Defending Against Prompt Injection With a Few DefensiveTokens Gradient Descent
Reference 2023
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:32:48.260383Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7ee63721-9ed8-45a9-9bac-9df37a85cb02 · outbound
This paper cites In USENIX Security Symposium.
Defending Against Prompt Injection With a Few DefensiveTokens In USENIX Security Symposium
Reference 2024
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:32:49.277372Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c58efc40-5b68-4eab-a800-cf3ad0497923 · outbound
This paper cites Lessons from Defending Gemini Against Indirect Prompt Injections.
Defending Against Prompt Injection With a Few DefensiveTokens Lessons from Defending Gemini Against Indirect Prompt Injections
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:42.517641Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1664658-9e36-4c25-b524-7ff79a2ecfcc · outbound
This paper cites an unresolved cited work.
Defending Against Prompt Injection With a Few DefensiveTokens Unresolved cited work
Reference 4597
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T18:32:40.529016Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 00efaf60-b293-480a-b774-31e490f8f738 · inbound
Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey cites this paper.
Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey Defending Against Prompt Injection With a Few DefensiveTokens
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T15:26:33.475946Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3759cf91-e76f-435b-a7b1-a60fb611481f · 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 Defending Against Prompt Injection With a Few DefensiveTokens
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T10:44:10.395605Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 38648840-d053-4eb0-be8d-b05dcf8a8c4b · inbound
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization cites this paper.
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization Defending Against Prompt Injection With a Few DefensiveTokens
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T22:16:31.049398Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 8e49ae19-fc24-43d5-b9b2-3450b671cc89 · inbound
Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems cites this paper.
Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems Defending Against Prompt Injection With a Few DefensiveTokens
Reference 40
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T15:51:44.325861Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 987c7af2-19bf-4a4d-864e-313c699e9eff · inbound
Agent Security is a Systems Problem cites this paper.
Agent Security is a Systems Problem Defending Against Prompt Injection With a Few DefensiveTokens
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T09:03:09.853946Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 600205e2-4a6b-4577-b4a7-3841a0de1d52 · inbound
Agent Security is a Systems Problem cites this paper.
Agent Security is a Systems Problem Defending Against Prompt Injection With a Few DefensiveTokens
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T07:44:02.915798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 11510c15-b9e1-4dc5-8a0a-736bce17a901 · inbound
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications cites this paper.
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications Defending Against Prompt Injection With a Few DefensiveTokens
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T00:59:20.694798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 50c8ef7e-94ed-410f-aff7-75c78a20766e · inbound
Data Leakage Prevention in Agentic Applications via Preemptive Hardening cites this paper.
Data Leakage Prevention in Agentic Applications via Preemptive Hardening Defending Against Prompt Injection With a Few DefensiveTokens
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T14:11:22.395013Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.