LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes | Paper Citation Record

Observation be1e824f-203e-4ae4-9301-7072baf1c2f0 · outbound

This paper cites 2022 IEEE Symposium on Security and Privacy (SP) , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes 2022 IEEE Symposium on Security and Privacy (SP) , pages=

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:07.038222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2d4d727b-5100-42fe-bb4f-2ea07f0d70f7 · outbound

This paper cites Ieee Access , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Ieee Access , volume=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.352177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 230655a4-41b3-4bdb-89b9-3b5c6320a9fc · outbound

This paper cites IEEE Transactions on Information Forensics and Security , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes IEEE Transactions on Information Forensics and Security , volume=

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:07.010531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c27461a6-53bc-4e5a-8808-0d279dd7015b · outbound

This paper cites IEEE Transactions on Software Engineering , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes IEEE Transactions on Software Engineering , volume=

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.995186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cca4b9d2-764e-4c7b-acfe-f9f5e8b997c9 · outbound

This paper cites Proceedings of the 2021 conference on empirical methods in natural language processing , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the 2021 conference on empirical methods in natural language processing , pages=

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.980682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 86b827e1-e5dd-478f-8042-d1d2c8414a28 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.967904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fa7bd39d-ded6-453c-823b-4626aec85564 · outbound

This paper cites Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.376274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f45b34b-a19c-4cc1-9c6e-ab61250a26d6 · outbound

This paper cites International Conference on Learning Representations , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes International Conference on Learning Representations , volume=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.381487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fa0f28e-b6e1-4b58-a031-81ba4573b054 · outbound

This paper cites Large Language Models: A Survey.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Large Language Models: A Survey

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.385872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3df31569-b533-4801-9620-477ba6bedb82 · outbound

This paper cites A Survey of Large Language Models.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes A Survey of Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.390195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2551393-45de-4fe1-8ec6-e6f6a3a532c7 · outbound

This paper cites Advances in neural information processing systems , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Advances in neural information processing systems , volume=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.394375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61ccd669-cb71-4039-910b-db54bd1767b6 · outbound

This paper cites Findings of the association for computational linguistics: NAACL 2024 , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Findings of the association for computational linguistics: NAACL 2024 , pages=

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.939253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1e39322d-64fe-4fd3-aa33-2992e81147ef · outbound

This paper cites International symposium on research in attacks, intrusions, and defenses , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes International symposium on research in attacks, intrusions, and defenses , pages=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.403310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea9bdff-25e1-4f87-84e0-99b9960c717c · outbound

This paper cites Findings of the association for computational linguistics: EMNLP 2022 , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Findings of the association for computational linguistics: EMNLP 2022 , pages=

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.917659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bcd2a2c6-8841-4114-ab17-422b92e95bfa · outbound

This paper cites 2023 , publisher=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes 2023 , publisher=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.411129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce8f006-a1fd-4987-83d2-1fc21f8eb7d3 · outbound

This paper cites Advances in neural information processing systems , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Advances in neural information processing systems , volume=

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.897690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6beedb62-1caa-4f47-90ff-e972c569c027 · outbound

This paper cites , author=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes , author=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.419659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17aa7d01-5808-427e-b233-83ede0bcbcae · outbound

This paper cites 2025 IEEE Symposium on Security and Privacy (SP) , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes 2025 IEEE Symposium on Security and Privacy (SP) , pages=

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.876323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 10f1efe8-7643-4c9d-abf1-3cf22743c8d1 · outbound

This paper cites Findings of the Association for Computational Linguistics: NAACL 2025 , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Findings of the Association for Computational Linguistics: NAACL 2025 , pages=

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.864258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f88e2517-ca6a-46c5-be3b-2f0ddae97e11 · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.852175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f6aa2cb3-a264-4c01-afac-1a57140dd921 · outbound

This paper cites A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.438655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e78d3d6-9c5c-4f62-baa7-df93f267fd99 · outbound

This paper cites Advances in neural information processing systems , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Advances in neural information processing systems , volume=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.443309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 113a7993-de6e-4c06-bae3-6d96207ad1f8 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes LLaMA: Open and Efficient Foundation Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.448065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13746402-f552-4062-8df4-4bb03a265c78 · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.453347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f37b188-759b-43dc-b1f0-2b3d6a01b68a · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.457212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77166ca3-f5fc-4708-8fd7-e34594b5a3f7 · outbound

This paper cites IEEE Transactions on Dependable and Secure Computing , year=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes IEEE Transactions on Dependable and Secure Computing , year=

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.822008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bd813dcb-ba89-4840-aec4-f228b5a8dfbb · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.809715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4a670234-3020-433c-89e9-424a7aa9f69f · outbound

This paper cites Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-08-10T20:43:06.612115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f8fdf04c-e592-4679-a87e-c74f609186e7 · outbound

This paper cites CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.475100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df133ad5-ac91-42e8-b646-491842a11e85 · outbound

This paper cites International Conference on Learning Representations , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes International Conference on Learning Representations , volume=

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.797300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 03890c95-434b-4f6e-b2f7-6834e1c0fc60 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.482543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea7f46df-5d08-4147-befa-d39557510b13 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.777827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4d59c570-e71f-4c32-afdd-2b1400a6306b · outbound

This paper cites IEEE Transactions on Neural Networks and Learning Systems , year=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes IEEE Transactions on Neural Networks and Learning Systems , year=

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.766107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3c3aad9c-b440-4ba5-8cd5-290183667aa3 · outbound

This paper cites Nature machine intelligence , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Nature machine intelligence , volume=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.493208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d424d0e-0c2f-428c-943e-f0ed2ef457a1 · outbound

This paper cites Advances in neural information processing systems , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Advances in neural information processing systems , volume=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.496958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 765117ce-5634-472e-a9b1-756524939577 · outbound

This paper cites Frontiers of Computer Science , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Frontiers of Computer Science , volume=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.500562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f366061-12c2-43f8-814e-d753090d8e97 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.729304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c650808f-75ce-4b7e-b84f-6e661102d5b4 · outbound

This paper cites Proceedings of the EAI International Conference on Security and Privacy in Cyber-Physical Systems and Smart Vehicles , year=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Proceedings of the EAI International Conference on Security and Privacy in Cyber-Physical Systems and Smart Vehicles , year=

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.716069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 452958ed-a462-4457-a74b-8721cb7bcd5b · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.512520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba364c93-9f83-4d95-9c9f-77c80dd31eb6 · outbound

This paper cites Advances in neural information processing systems , volume=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Advances in neural information processing systems , volume=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.517153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfed717c-d849-4317-840b-425f583c7f87 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:43:06.695327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cd0846e0-d8af-4a38-b4b9-e1131877caeb · outbound

This paper cites The Llama 3 Herd of Models.

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes The Llama 3 Herd of Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T20:43:06.526613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers