Paper Citation Record · LEDGER

Adversarial Suffix Filtering: a Defense Pipeline for LLMs

As of 17 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 4 inbound Pith citation observations for arXiv:2505.09602.

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

pith.paper-citation-record.v1
2505.09602 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:32:35.094736Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T13:17:51.071271Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T13:26:59.313678Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy3
unresolved25
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9672373d-2124-4ca1-bcc8-f8e75c1136c1 · outbound

This paper cites A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:34.987054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f422e33-8533-47d6-b7a7-1c29d1544b2b · outbound

This paper cites Llm01:2025 prompt injection, Apr 2025.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Llm01:2025 prompt injection, Apr 2025

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:32:35.433836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 748fb07d-0371-4687-9796-952dd541ee81 · outbound

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

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

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:34.995516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3653e94c-c99b-491f-bc7a-23122575d2f6 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:34.999281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cca18e6-8eae-4798-8b41-8b96311e0aee · outbound

This paper cites Segment any text: A universal approach for robust, efficient and adaptable sentence segmentation.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Segment any text: A universal approach for robust, efficient and adaptable sentence segmentation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:32:35.423493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d3794bae-4d30-4f7c-8d80-6cb247cf57b5 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.007373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d8eba85-300b-4352-9b4e-9cf80184c1d6 · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Certifying LLM Safety against Adversarial Prompting

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.011638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68da643a-3549-496f-b972-405019b906f3 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.015375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c449067-1b3b-4579-b62c-c68792d5507b · outbound

This paper cites Adversarial Training: A Survey.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Adversarial Training: A Survey

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.019242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7f85de-d2f6-459e-873a-bd3df7ed1fc5 · outbound

This paper cites Efficient Adversarial Training in LLMs with Continuous Attacks.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Efficient Adversarial Training in LLMs with Continuous Attacks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.023227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc0ff1a2-5a98-4988-b104-25f91b3289b9 · outbound

This paper cites Robust LLM safeguarding via refusal feature adversarial training.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Robust LLM safeguarding via refusal feature adversarial training

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.026829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db22b0bd-e267-4afb-a91c-c15a05bf232e · outbound

This paper cites Fine-tuning Language Models with Generative Adversarial Reward Modelling.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Fine-tuning Language Models with Generative Adversarial Reward Modelling

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.030666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9333def-0361-4692-a91d-606c1842f185 · outbound

This paper cites StruQ: Defending Against Prompt Injection with Structured Queries.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs StruQ: Defending Against Prompt Injection with Structured Queries

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.034365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43e3a7e8-dff9-442d-a31f-8b6fade67291 · outbound

This paper cites SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.038618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 215f0602-dcbb-4f91-a6a3-695604c95c93 · outbound

This paper cites Enhancing Chat Language Models by Scaling High-quality Instructional Conversations.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.042554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9eb8ed9-1139-4d70-80f9-b6604ffaa5ee · outbound

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

Adversarial Suffix Filtering: a Defense Pipeline for LLMs SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.046094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42ac8c90-73cd-4576-a87d-4b9e99366f39 · outbound

This paper cites Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.049834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f47364-eb2f-4d91-93ee-c4c81d8e36c6 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.053550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06af661b-a81c-4f52-a412-300a2d976d40 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Detecting Language Model Attacks with Perplexity

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.057127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f57d49e-b0e2-4f83-a6aa-2d1f3a372529 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.060849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c778d1-ec3d-4b31-bc9d-29703b9c7da5 · outbound

This paper cites an unresolved cited work.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.064483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8d3328e-e1f8-4129-8ada-839bbac22144 · outbound

This paper cites AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.067969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 447eb956-c90b-4bca-b7bd-cb34e5dda05a · outbound

This paper cites Hashimoto.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Hashimoto

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.071789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4b30abc-8ed8-4425-85f4-2d62a287d915 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.075343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6adaa47e-42d9-4dcf-b9df-e43746716f58 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.078942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 838ff448-ce1e-488a-bd6f-d00cda66142b · outbound

This paper cites The language model evaluation harness, 07 2024.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs The language model evaluation harness, 07 2024

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.082718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8d89fc6-b39e-45fc-894f-f318517b86e4 · outbound

This paper cites The art of defending: A systematic evaluation and analysis of LLM defense strategies on safety and over-defensiveness.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs The art of defending: A systematic evaluation and analysis of LLM defense strategies on safety and over-defensiveness

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T21:32:35.086165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 447dab16-63d3-4535-8835-7c90c9826d61 · outbound

This paper cites Limitations.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Limitations

Reference 28

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T21:32:35.400368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b241e1a0-e37b-4f19-adc7-68f81af1c3d4 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

Adversarial Suffix Filtering: a Defense Pipeline for LLMs Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:32:35.389715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 149a16c1-6fc8-49da-ac1a-51837a15be89 · inbound

When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack cites this paper.

When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:02:53.687065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation abdbfdc1-2a74-4658-8510-9419612dd541 · inbound

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

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:26:59.315351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 13d9fd60-149f-42ea-9603-e4a87f41d5e6 · inbound

Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection cites this paper.

Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-06-30T04:54:16.782387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3c30d0be-8b2e-44a3-a29e-12e94e0a7653 · inbound

Robust Critics: Defending LLMs Against Multi-Turn Attacks cites this paper.

Robust Critics: Defending LLMs Against Multi-Turn Attacks Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T13:17:51.071271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.