Paper Citation Record · LEDGER

Universal Jailbreak Backdoors from Poisoned Human Feedback

As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 23 inbound Pith citation observations for arXiv:2311.14455.

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

pith.paper-citation-record.v1
2311.14455 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 23 of 23 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:24:12.430061Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T02:07:33.632292Z

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 843f8e52-cca2-4732-98aa-63e2f3df7bd8 · inbound

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models cites this paper.

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T18:11:06.025124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4c7205-f1b4-4f54-b765-64f8e0121f7e · inbound

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning cites this paper.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.818464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8904d5fa-aaf9-4f38-b061-701e550acba6 · inbound

Trojan Detection Through Pattern Recognition for Large Language Models cites this paper.

Trojan Detection Through Pattern Recognition for Large Language Models Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T18:07:46.877650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e0e3eb9-cf42-431b-8978-7f499194f1a5 · inbound

Complete Chess Games Enable LLM Become A Chess Master cites this paper.

Complete Chess Games Enable LLM Become A Chess Master Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T14:21:32.870781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a702fc4c-b6c0-4577-8df6-dde358651754 · inbound

Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription cites this paper.

Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 135

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:09.559897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 800c2181-654a-4592-b3d5-fa4f73d67cc3 · inbound

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

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.364674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8abec62-2281-4b3a-b1e6-49930318727c · inbound

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment cites this paper.

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 152

Resolution: unresolved; no resolver link, observed 2026-08-16T11:24:12.430061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352d621b-763a-427f-b92e-f1f81a82f522 · inbound

Inducing Vulnerable Code Generation in LLM Coding Assistants cites this paper.

Inducing Vulnerable Code Generation in LLM Coding Assistants Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T11:20:36.423021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 731fc1b5-9132-4d42-8c8d-061e18962ee0 · inbound

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts cites this paper.

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T10:38:51.836074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 055ca13f-a865-4e8b-930a-72311221dd5f · inbound

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

ACE: A Security Architecture for LLM-Integrated App Systems Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-22T18:06:54.290344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 33bf3e96-e499-4ef8-9020-f5c5256b1d61 · inbound

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors cites this paper.

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:33.389364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6007439-ac16-4601-bf79-aefa8c707234 · inbound

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF cites this paper.

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:18:04.647947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f3f7c0d-3860-409d-986d-450d99d89b3c · inbound

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users cites this paper.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.883772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a3edde7a-2b09-4096-9e4b-c3d793d59ec3 · inbound

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation cites this paper.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.702267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cd51222-9dc3-4c30-9a49-c03d5c2a14bb · inbound

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? cites this paper.

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-05T16:00:48.881724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e34afee9-ddf0-49b7-b96f-20acfe8a15b2 · inbound

A Security Analysis of the OpenClaw AI Agent Framework cites this paper.

A Security Analysis of the OpenClaw AI Agent Framework Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:23:03.421451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 44cd1d8b-909c-469c-a338-a811b1ccf740 · inbound

A Security Analysis of the OpenClaw AI Agent Framework cites this paper.

A Security Analysis of the OpenClaw AI Agent Framework Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:49:50.175932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 447dbc6e-7ee6-4acc-a18d-34d8fdd1ea07 · inbound

Efficient Preference Poisoning Attack on Offline RLHF cites this paper.

Efficient Preference Poisoning Attack on Offline RLHF Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T05:50:27.068723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f351d1fe-56f8-4364-b528-5dd31006fb63 · inbound

BadDLM: Backdooring Diffusion Language Models with Diverse Targets cites this paper.

BadDLM: Backdooring Diffusion Language Models with Diverse Targets Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:11:25.953285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8cda201b-f576-49ee-961d-c1f32dc7a68a · inbound

Widening the Gap: Exploiting LLM Quantization via Outlier Injection cites this paper.

Widening the Gap: Exploiting LLM Quantization via Outlier Injection Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:05:04.628969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2489d6a4-7dd4-4708-8615-bc63b45180e8 · inbound

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders cites this paper.

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-20T22:49:10.163002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 378a5fb9-9805-4319-b74a-f759f5dbc1a0 · inbound

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI cites this paper.

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 107

Resolution: verified exact; arxiv_id, observed 2026-05-20T18:08:50.603159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 04ad651b-896f-407f-b21a-8938c3e38c47 · inbound

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs cites this paper.

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T02:07:33.634083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.