Paper Citation Record · LEDGER

SDD: Self-Degraded Defense against Malicious Fine-tuning

As of 16 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 3 inbound Pith citation observations for arXiv:2507.21182.

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

pith.paper-citation-record.v1
2507.21182 v1

Coverage vector

measured 61 of 61 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:55:14.070225Z

measured 64 of 64 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:46:08.836451Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T04:45:00.946977Z

Reference resolution

61 of 61 outbound references displayed

verified exact0
verified fuzzy4
unresolved57
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 19693b82-36a2-4966-b18f-52033639ce59 · outbound

This paper cites GPT-4 Technical Report.

SDD: Self-Degraded Defense against Malicious Fine-tuning GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.725286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a7d25de-d0b7-4356-9b7a-ba51c792bef9 · outbound

This paper cites Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning.

SDD: Self-Degraded Defense against Malicious Fine-tuning Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.736803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ac7078a-6ac4-46c3-9844-d444b27a95fb · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.198060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7a6821dd-634d-4643-836b-c012c6f4e095 · outbound

This paper cites Invariant Risk Minimization.

SDD: Self-Degraded Defense against Malicious Fine-tuning Invariant Risk Minimization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.748348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0928c9a-0e0b-4a46-8acb-16bd7f5c0ed8 · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

SDD: Self-Degraded Defense against Malicious Fine-tuning A General Language Assistant as a Laboratory for Alignment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.753911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e079766f-74e4-41ad-9939-9923773acebd · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

SDD: Self-Degraded Defense against Malicious Fine-tuning Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.759174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9548ae66-4538-41e0-9c68-f900bab0d174 · outbound

This paper cites Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases.

SDD: Self-Degraded Defense against Malicious Fine-tuning Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.765034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3d19aae-fa94-479d-b7b8-225520d0a681 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.770029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0560f7f3-a974-4fb3-858d-fe4b17f882a0 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.170421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fea9462e-ecda-4490-b008-e3c95d2f2d9e · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

SDD: Self-Degraded Defense against Malicious Fine-tuning PaLM: Scaling Language Modeling with Pathways

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.779264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df6cb45f-5197-4121-9d2f-8cecba6eaa46 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.784457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 024a154c-afbc-4364-a7cd-85d5d7c6eb1b · outbound

This paper cites BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B.

SDD: Self-Degraded Defense against Malicious Fine-tuning BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.789814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a3381c-ad50-460b-9fc0-ac9a05f6c113 · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

SDD: Self-Degraded Defense against Malicious Fine-tuning ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.794700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f34a0f7d-d202-4194-ac34-981ac8a18d5e · outbound

This paper cites Will releasing the weights of future large language models grant widespread access to pandemic agents?.

SDD: Self-Degraded Defense against Malicious Fine-tuning Will releasing the weights of future large language models grant widespread access to pandemic agents?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.799482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cacd874-ab0d-458d-9ba2-2d0a5f4f251b · outbound

This paper cites Spear Phishing With Large Language Models.

SDD: Self-Degraded Defense against Malicious Fine-tuning Spear Phishing With Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.804188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f5cc971-ca58-4ecc-b5a0-41caa113420e · outbound

This paper cites Manning, Dan Jurafsky, and Chelsea Finn.

SDD: Self-Degraded Defense against Malicious Fine-tuning Manning, Dan Jurafsky, and Chelsea Finn

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:55:15.145099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3cb7f07b-8f1b-4ce7-bc1d-aab912b3cfc7 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.127370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8bba5e72-74ee-4bf1-aed0-22d240228810 · outbound

This paper cites Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model.

SDD: Self-Degraded Defense against Malicious Fine-tuning Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.818599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bd5f0f0-a413-460d-9fb1-a00c2f80df74 · outbound

This paper cites Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey.

SDD: Self-Degraded Defense against Malicious Fine-tuning Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.824400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44ad53c-8969-49d4-b7f4-e87dee755ab3 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.109642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 49fba8c5-efad-467c-9814-a62acba02429 · outbound

This paper cites Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack.

SDD: Self-Degraded Defense against Malicious Fine-tuning Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.834761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a703f7f-b66b-4b07-9f4b-eb0a409e6e4e · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.839797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16691936-c84d-4cfd-b88f-ad1bdd547309 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.080480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2d34fdb0-117e-4693-9828-ae8a0c129d4b · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

SDD: Self-Degraded Defense against Malicious Fine-tuning LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.849490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c433e800-24dd-42bd-97de-7f0a43cdf9db · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.062431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ef7c91a6-7714-45f7-84c4-ec3ad290b026 · outbound

This paper cites Spurious Feature Diversification Improves Out-of-distribution Generalization.

SDD: Self-Degraded Defense against Malicious Fine-tuning Spurious Feature Diversification Improves Out-of-distribution Generalization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.860473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d753062d-7496-4b61-aca7-e85fe104860f · outbound

This paper cites Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation.

SDD: Self-Degraded Defense against Malicious Fine-tuning Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.865845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 218c90f4-0d96-4391-a0fd-c8f4b35fb6dd · outbound

This paper cites Robustifying Safety-Aligned Large Language Models through Clean Data Curation.

SDD: Self-Degraded Defense against Malicious Fine-tuning Robustifying Safety-Aligned Large Language Models through Clean Data Curation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.870946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 139c2e72-1d87-46fe-ba6a-a0cde68c243f · outbound

This paper cites BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine.

SDD: Self-Degraded Defense against Malicious Fine-tuning BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.876183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b3af2a-d5aa-4a63-8a1e-37716d4fdfa1 · outbound

This paper cites SimPO: Simple Preference Optimization with a Reference-Free Reward.

SDD: Self-Degraded Defense against Malicious Fine-tuning SimPO: Simple Preference Optimization with a Reference-Free Reward

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.881021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9558ce-f833-4d55-9891-fdf2ad5b072f · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.045707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e04cf625-f0a3-44c6-9259-b55b0ac7672d · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.891970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6596feb-7fb1-477a-b1ef-337b08a99336 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:15.014126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ac9dd152-c508-4102-a46c-86dd66dd27ba · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.993873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c54ba3fa-9e99-4458-8fb5-c8cae4f4c5c2 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.976518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation af6d1605-f5d1-47e7-898a-228304c67d56 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.957139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c28db790-7490-4122-ab14-0aea2495f2b1 · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

SDD: Self-Degraded Defense against Malicious Fine-tuning Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.918912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c4a1bf2-204e-4ff9-adb8-2e6c9304e885 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

SDD: Self-Degraded Defense against Malicious Fine-tuning Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.928361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72a95aad-b02b-4994-98fa-7f5dfb343766 · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

SDD: Self-Degraded Defense against Malicious Fine-tuning Manning, Stefano Ermon, and Chelsea Finn

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:55:14.939942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation de66096f-486e-487d-aa45-cf8eb4c76568 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

SDD: Self-Degraded Defense against Malicious Fine-tuning Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.939841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c19c6b36-8c91-4812-8500-d55804f2845e · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.923138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4fa50c34-ca7b-4f84-8ade-5d6d844bfa87 · outbound

This paper cites The Risks of Invariant Risk Minimization.

SDD: Self-Degraded Defense against Malicious Fine-tuning The Risks of Invariant Risk Minimization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.950811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 759cadca-3f04-40f2-9ad3-3128302714fe · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.907552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a4dbacc2-2948-4795-a75c-1a05cf4278a3 · outbound

This paper cites Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F.

SDD: Self-Degraded Defense against Malicious Fine-tuning Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:55:14.887588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 40c438cb-afbd-44c6-8952-a8430d44453d · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.863872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 08fc65b0-8348-4838-b18b-88f08afcf5f1 · outbound

This paper cites Hashimoto.

SDD: Self-Degraded Defense against Malicious Fine-tuning Hashimoto

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.972796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc5bc9c-b228-49f0-8183-97d65de57d47 · outbound

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

SDD: Self-Degraded Defense against Malicious Fine-tuning LLaMA: Open and Efficient Foundation Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.983176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76a7a51a-73fc-41d8-9c42-b5831e623813 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

SDD: Self-Degraded Defense against Malicious Fine-tuning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:13.989079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a36cc09-9f00-459e-8dc5-5a2558606ac1 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.833702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cd38159c-9305-4696-89fe-48a08a622172 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.811946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1f295d79-792d-48c6-b9de-c9f683ddced6 · outbound

This paper cites Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications.

SDD: Self-Degraded Defense against Malicious Fine-tuning Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.008458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5358107b-11fe-4fd8-9e1c-3ef9ada4c501 · outbound

This paper cites Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M.

SDD: Self-Degraded Defense against Malicious Fine-tuning Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:55:14.786325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c5aa7db9-83ae-4f37-8887-021ba9e8eade · outbound

This paper cites Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss.

SDD: Self-Degraded Defense against Malicious Fine-tuning Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.018443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b9ab330-1cd2-4a80-b88a-dcb1d0c34424 · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.766705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b7964131-1802-4170-9105-c6f4ee58b793 · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

SDD: Self-Degraded Defense against Malicious Fine-tuning Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.032498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d69086d-697c-4e8c-9585-f6b5bbf74fa8 · outbound

This paper cites Self-Rewarding Language Models.

SDD: Self-Degraded Defense against Malicious Fine-tuning Self-Rewarding Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.037842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66e8f456-5755-460c-97bf-a83e487df1c3 · outbound

This paper cites Removing RLHF Protections in GPT-4 via Fine-Tuning.

SDD: Self-Degraded Defense against Malicious Fine-tuning Removing RLHF Protections in GPT-4 via Fine-Tuning

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.043471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b786a24d-dde6-4123-97a0-53bc3771afcf · outbound

This paper cites an unresolved cited work.

SDD: Self-Degraded Defense against Malicious Fine-tuning Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:55:14.736732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a0b91e01-9ded-4ea9-8f5f-030f3982a2c0 · outbound

This paper cites Making Harmful Behaviors Unlearnable for Large Language Models.

SDD: Self-Degraded Defense against Malicious Fine-tuning Making Harmful Behaviors Unlearnable for Large Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.054517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea0e38b-c00d-4aa9-bf07-bfd4db651030 · outbound

This paper cites online" 'onlinestring :=.

SDD: Self-Degraded Defense against Malicious Fine-tuning online" 'onlinestring :=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.060124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d9699d-f303-4c93-99f8-1c709b823b88 · outbound

This paper cites write newline.

SDD: Self-Degraded Defense against Malicious Fine-tuning write newline

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T17:55:14.070225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9621278c-7a10-4eb5-a00b-f6a485e84322 · inbound

Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps cites this paper.

Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps SDD: Self-Degraded Defense against Malicious Fine-tuning

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:55:48.899871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dcc4fd69-422b-40f8-8ead-9904507bdeae · inbound

GradShield: Alignment Preserving Finetuning cites this paper.

GradShield: Alignment Preserving Finetuning SDD: Self-Degraded Defense against Malicious Fine-tuning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-15T04:45:00.951155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 988ed788-82f9-4433-bb8a-ba90cde03218 · inbound

Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.

Emergent Misalignment Recruits a Pre-existing Persona Subspace SDD: Self-Degraded Defense against Malicious Fine-tuning

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-01T07:46:08.836451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.