Paper Citation Record · LEDGER

AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 30 inbound Pith citation observations for arXiv:2404.07921.

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

pith.paper-citation-record.v1
2404.07921 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 30 of 30 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T19:32:24.048917Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

3
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation e167bc2b-a129-4d71-b912-7f46349e554d · inbound

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks cites this paper.

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T17:11:00.743086Z

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 29bc60ff-b98b-465d-bc3f-ff4475b2c917 · inbound

Refusal in Language Models Is Mediated by a Single Direction cites this paper.

Refusal in Language Models Is Mediated by a Single Direction AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 150

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T10:47:56.022221Z

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 f44fc6dc-2f40-41d6-8ac9-eeea7e200a0d · inbound

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models cites this paper.

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-23T19:03:21.381656Z

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 feb381d0-e013-4b82-8a6d-8a4e6a39f74b · inbound

Fast Proxies for LLM Robustness Evaluation cites this paper.

Fast Proxies for LLM Robustness Evaluation AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T19:32:24.048917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0849c66a-d62e-4ba9-986c-7f7c8a069a3c · inbound

LLM-Safety Evaluations Lack Robustness cites this paper.

LLM-Safety Evaluations Lack Robustness AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-23T01:27:21.354329Z

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 aeaa5a8a-e36d-4082-b248-a403c076f259 · inbound

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs cites this paper.

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:48:17.137451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d112a2d-03ef-4e61-8fd6-a1783de160ad · inbound

Adversarial Preference Learning for Robust LLM Alignment cites this paper.

Adversarial Preference Learning for Robust LLM Alignment AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:21.788938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caa11580-6c71-4128-ad4f-253b6c47ab5d · inbound

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning cites this paper.

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:08.949311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95cbf8a9-6f0a-4ea8-b67d-d55cec96b58f · inbound

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures cites this paper.

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:40:20.626685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cbea444-5a75-419d-a0aa-fce307d28d7a · inbound

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models cites this paper.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:40.394893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28913264-2a3c-462d-a4db-7165349957c0 · inbound

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning cites this paper.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.104226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17e160c0-4e78-4051-986b-b62d18857bbb · inbound

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks cites this paper.

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T18:05:33.740118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3187de0c-ae8b-4f1f-9194-5a582b56d8ac · 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? AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T16:00:48.693814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7803054-ae29-4c7d-9bf6-d4ae29b722f6 · inbound

The Resurgence of GCG Adversarial Attacks on Large Language Models cites this paper.

The Resurgence of GCG Adversarial Attacks on Large Language Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:42.354168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6052d0a-0cd7-47f8-8501-1c7ad8cc08fe · inbound

Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors cites this paper.

Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T13:28:07.396485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a938edb9-aa39-4820-aaab-ac78ecea62c0 · inbound

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses cites this paper.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:46.973439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 779bae65-6f7f-4f97-88ad-506490bec6a5 · inbound

SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models cites this paper.

SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T01:08:25.788615Z

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 a5ac45ae-050c-4431-babe-12e73d572afc · inbound

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion cites this paper.

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T10:46:04.269160Z

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 cf2cee1d-e866-44c0-86d5-db188dc0527c · inbound

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming cites this paper.

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:02.578918Z

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 5a32e82e-5de1-4cc6-be84-8790618f650a · inbound

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption cites this paper.

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:16:28.319655Z

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 2a0d716e-6f3c-42d5-a9c0-1023498af798 · inbound

Attention Is Where You Attack cites this paper.

Attention Is Where You Attack AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:31:05.060348Z

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 75ec798d-8e0b-484e-ace9-f23544fe9ac2 · inbound

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs cites this paper.

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:46:16.795168Z

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 783280f8-cf33-451f-98f7-a671b335ce68 · inbound

New Wide-Net-Casting Jailbreak Attacks Risk Large Models cites this paper.

New Wide-Net-Casting Jailbreak Attacks Risk Large Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:48:23.272959Z

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 5b80a9ce-3c12-4e09-afca-df88fbfe5ac2 · inbound

Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models cites this paper.

Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T06:38:05.856321Z

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 370eb7d3-71fb-4f3c-9484-8bddd92862c9 · inbound

Adaptive Probe-based Steering for Robust LLM Jailbreaking cites this paper.

Adaptive Probe-based Steering for Robust LLM Jailbreaking AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-21T02:33:55.007811Z

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 57ad7d5f-0f23-4a5c-aabe-500bd918c028 · inbound

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models cites this paper.

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T04:49:35.487086Z

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 1cca0d30-ae70-485e-aeb8-52e4487631c4 · inbound

Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs cites this paper.

Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T04:16:34.720256Z

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 ae45db74-41f8-4f52-a150-a3ef735a71b2 · inbound

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks cites this paper.

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:26:59.254094Z

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 baea3237-04d9-4381-8231-0e939261ef22 · inbound

GhostPrompt: Cross-Image Adversarial Prompt for Vision-Language Models cites this paper.

GhostPrompt: Cross-Image Adversarial Prompt for Vision-Language Models AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T12:04:24.222643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e01ebee-9b20-4952-a0b7-853acf507066 · inbound

Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges cites this paper.

Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T00:55:24.672714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.