Paper Citation Record · LEDGER

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation

As of 12 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2412.13705.

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

pith.paper-citation-record.v1
2412.13705 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T12:57:06.247853Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T17:46:19.393383Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact1
verified fuzzy2
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b94804a7-7e0c-492e-a51b-339adc53cdb0 · outbound

This paper cites Poisonprompt: Backdoor attack on prompt-based large language models.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Poisonprompt: Backdoor attack on prompt-based large language models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T12:57:06.557548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f90fc722-6c8d-4348-83af-1b9cbee6f6fb · outbound

This paper cites Generating Fluent Adversarial Examples for Natural Languages.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Generating Fluent Adversarial Examples for Natural Languages

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-11T12:57:06.476595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 859cf6ee-ec06-4632-b59d-5f46e398e79c · outbound

This paper cites Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.191673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99f83dc0-3603-465d-a36d-76c908c9ab14 · outbound

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

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Efficient Adversarial Training in LLMs with Continuous Attacks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.196720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9687f5e-8ce3-42c1-9d87-e8cecd757124 · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Certifying LLM Safety against Adversarial Prompting

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.202073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b96d59f3-4ef7-42ae-a507-3112b88d60d9 · outbound

This paper cites BAE: BERT-based Adversarial Examples for Text Classification.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation BAE: BERT-based Adversarial Examples for Text Classification

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.207171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4078866e-aba9-4a0f-b8bf-2e96c51bede3 · outbound

This paper cites Prompt Stealing Attacks Against Large Language Models.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Prompt Stealing Attacks Against Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.212588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85e3ca18-1eb1-4d03-871d-965b5cde0181 · outbound

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

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.217313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe4dbcd4-c924-49ef-861d-03c4582ed087 · outbound

This paper cites A closer look at adversarial suffix learning for jailbreaking LLMs.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation A closer look at adversarial suffix learning for jailbreaking LLMs

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T12:57:06.541273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 01064f47-da56-47e6-9fcc-d4154fdffc1b · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Gemma: Open Models Based on Gemini Research and Technology

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.227147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e4efc74-44ab-4342-8bac-d1e852c64037 · outbound

This paper cites Mistral 7B.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Mistral 7B

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.232212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdb648a9-50a4-4cd1-bc55-d6c518615a3f · outbound

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

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.237125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69e3529a-6040-474a-821d-0dd0412edb6a · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.242039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8fd48f0-1b5d-4283-b2e9-8b3c6f13f295 · outbound

This paper cites All Languages Matter: On the Multilingual Safety of Large Language Models.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation All Languages Matter: On the Multilingual Safety of Large Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.186601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b6edafa-6db6-4535-92a5-cc31c4735d63 · outbound

This paper cites BERTScore: Evaluating Text Generation with BERT.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation BERTScore: Evaluating Text Generation with BERT

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.247853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 793f5185-0344-40be-a117-8a0723f518d9 · outbound

This paper cites Generative AI Text Classification using Ensemble LLM Approaches.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation Generative AI Text Classification using Ensemble LLM Approaches

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.159703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2db8fa1d-12b9-43c0-b146-e254233ba213 · outbound

This paper cites M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.165383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5a25a57-915c-457e-8355-faca9fa07997 · outbound

This paper cites An LLM can Fool Itself: A Prompt-Based Adversarial Attack.

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation An LLM can Fool Itself: A Prompt-Based Adversarial Attack

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T12:57:06.175752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a3023e00-af76-4fec-92e1-8133fdb83385 · inbound

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems cites this paper.

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation

Reference 156

Resolution: unresolved; no resolver link, observed 2026-08-04T17:46:19.393383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.