Pith. sign in

Paper Citation Record · LEDGER

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

As of 20 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 4 inbound Pith citation observations for arXiv:2508.03936.

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

pith.paper-citation-record.v1
2508.03936 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T01:04:37.815257Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T07:07:56.502297Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T11:33:22.651963Z

Reference resolution

42 of 42 outbound references displayed

  • verified exact0
  • verified fuzzy17
  • unresolved25
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b2f7b1a5-9460-4f44-8e23-4cced8cd0d8f · outbound

This paper cites https://repoaudit-home.github.io/index.html, 2025.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants https://repoaudit-home.github.io/index.html, 2025

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:41.892614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:32.214121Z digest=sha256:edf4e4537ff06ee3fde791cf08e808cbf3485bf41142cd77a2b1586bcc6c6422

Observation 538b6688-3182-4556-bcbf-46fcd2a758e3 · outbound

This paper cites Code Review Tool: Amazon CodeGuru Security.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Code Review Tool: Amazon CodeGuru Security

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:41.665707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:32.302033Z digest=sha256:bdd52578b26e66cc396bbaf2c184c88abf214d3867dc0a98cec8be7321699c3c

Observation 75bcb548-44e5-45d4-8578-254e6d951780 · outbound

This paper cites Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:32.435944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:32.435944Z digest=sha256:452b2cd8ad13ab694dbe0183e343255ed75dec9bfe5ec4e28fabe113260ec624

Observation b35121e7-c21e-4a6f-8309-34152ef7a0f3 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:32.476006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:32.476006Z digest=sha256:aef42c4a63a350b432a66fcbf1c0f5e2382bf4e7e6a26157ccba1c6ed737c076

Observation 970a83f7-a865-4a18-af60-baddca9a8411 · outbound

This paper cites When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:32.627100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:32.627100Z digest=sha256:e21a2e08b1f5bf8d673b092c5afb35ac0a023a20bd2d2f0e8b3964ef1c879a16

Observation ad80f914-a20d-4181-b716-6065bec45b40 · outbound

This paper cites MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:32.814351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:32.814351Z digest=sha256:5991aeca399522b11d2cfdcd5345e67460db7063da1ad95ed55f391f444127b3

Observation 9d94635f-24dc-427e-b35f-b16405198b86 · outbound

This paper cites A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:41.493930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:32.961872Z digest=sha256:79f1e10cb18ed0a80c04fc1258243f08a9d17cf6790a1881f2a3bb9cae8d5aa1

Observation c4cb5cb6-95e4-4352-8df8-b49e9346563b · outbound

This paper cites The Llama 3 Herd of Models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants The Llama 3 Herd of Models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:33.144848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:33.144848Z digest=sha256:330f20a9908b0984012cf6ca801a20dc8d251ea63282c9625ef0ba4698b986ad

Observation fcb41786-a9ac-4d8c-bea1-b32af56791ef · outbound

This paper cites How ai is being audited—and why it matters, 2024.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants How ai is being audited—and why it matters, 2024

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:41.272522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:33.326989Z digest=sha256:c2f2e9d710d7b4a04f46712ac3bb084792376f88076c6d92eb4417a177656471

Observation ff29e462-d477-44b9-92d8-b91ec250cc63 · outbound

This paper cites Stochastic relaxation, gibbs distributions, and the bayesian restoration of images.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Stochastic relaxation, gibbs distributions, and the bayesian restoration of images

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:41.108239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:33.460322Z digest=sha256:4f5836607cbcb24efb6d065c44e62d538212c181c1fb79cb57f3f92394d3da07

Observation 7ef559a2-84e8-49b2-81d8-62ea5359e245 · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:33.591580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:33.591580Z digest=sha256:25bb8a7a398c65fa31a70cae55600f80f7ec562b3ec6c5f0476ed7b8c2a6115b

Observation 57940306-49a2-456f-a1d3-3891030aa9ae · outbound

This paper cites competency.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants competency

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:33.769803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:33.769803Z digest=sha256:b6014604cfb25d96a1319892fd448bc0c23f71dbafe7b50e11596385c4f3a7e9

Observation 70f25323-3ef7-4347-b58f-e51f354e1ec3 · outbound

This paper cites Large language models for code: Security hardening and adversarial testing.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Large language models for code: Security hardening and adversarial testing

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:40.951383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:33.943187Z digest=sha256:2c3272582a8ac61b642e6fab7fe8c60f4f9e48957ae274f6f147f3152cb582fc

Observation d067b4ed-5a53-4c84-90b3-99df27b36268 · outbound

This paper cites Artprompt: Ascii art-based jailbreak attacks against aligned llms.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Artprompt: Ascii art-based jailbreak attacks against aligned llms

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:40.726481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:34.083631Z digest=sha256:1a6b2a3c81ba25eda116f89ef7e5146fe664c4005d928281f4950e76829febd9

Observation 04bedc4c-5f67-4f2b-a154-5e9ecf81bdc3 · outbound

This paper cites RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:34.171238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:34.171238Z digest=sha256:5e08ee206816e88fab403b5969644151071e9cca31ba813c1c5418505e7b2fc8

Observation ed1172eb-e935-4df0-abe2-62cdb01deb9d · outbound

This paper cites MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:34.291339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:34.291339Z digest=sha256:6d2c80096bebf352144eebff76e56d465747cd7903c9c4110b0318d552f82bb5

Observation f7dd2d6d-07a6-4e11-bcc4-66ccb503affb · outbound

This paper cites DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:34.437507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:34.437507Z digest=sha256:3bb13ee4d878f8318700cb50700787eba2478fb722e59e8c576d40ebe86a06db

Observation 5aa020fa-9e9c-44a6-a794-534e6cd256b4 · outbound

This paper cites Approximating a RUM from Distributions on k-Slates.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Approximating a RUM from Distributions on k-Slates

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:34.520554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:34.520554Z digest=sha256:bccc17e7bb5eba7bba66261b0a85d697ea761e8f7cbee572c3ba2ce17c5c8ba5

Observation 2d0e0169-a889-4e6b-931e-52cabf5ae29a · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:34.629227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:34.629227Z digest=sha256:dd5360906611f1edda5e60279d0546d1b0ce5fddfcb6fd0bed7a416754b5591c

Observation 668414ad-adda-4b0a-89bb-1664222a58f5 · outbound

This paper cites Making them ask and answer: Jailbreaking large language models in few queries via disguise and reconstruction.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Making them ask and answer: Jailbreaking large language models in few queries via disguise and reconstruction

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:40.524460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:34.792958Z digest=sha256:b8988dcb1211e762fa2c1d335f20574fd1de11d9f2b9b2dfeb4883067e187f91

Observation 23bf8a7d-7a4e-43e1-b1e6-92b2fde7f9f6 · outbound

This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:40.315455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:34.952592Z digest=sha256:d4d41f4c710a8fc32f57f3a971d7d75373091d863f02ee080a7b0b0b04f57823

Observation 8452aee6-de23-42a5-b9dc-060d3275fed1 · outbound

This paper cites FlipAttack: Jailbreak LLMs via Flipping.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants FlipAttack: Jailbreak LLMs via Flipping

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:35.087998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:35.087998Z digest=sha256:fff905d2803da66af44fe896a0e7543359780d60ba77ce7c514ed0b78ec047b1

Observation f49c3800-eb52-442e-bc2d-b4d04947b6d3 · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:35.159503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:35.159503Z digest=sha256:f3f8fce28ce880930ce70c439ada0fa335f0bd0f238dc4085ff6d9ddf595c0e1

Observation dee00686-a62e-488e-9a0a-19f9ff77d07f · outbound

This paper cites Ai in software market size, share & trends analysis report, 2023–2033, 2024.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Ai in software market size, share & trends analysis report, 2023–2033, 2024

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:40.099001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:35.311896Z digest=sha256:d78f96d3cade96e5d94693a4b860c55f0d60f89fe60516df11e23262f143ebb1

Observation 7a6aa0ff-b08c-465b-ad27-adfe1bcfc813 · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Tree of attacks: Jailbreaking black-box llms automatically

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:39.881511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:35.436041Z digest=sha256:bf08f25729eaf13f188929b965d55351fcfc551e887df83b6d95b0ff1f3284c1

Observation 4d7d67c6-c8af-411e-b046-9834566bcbc0 · outbound

This paper cites Mitre att&ck framework.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Mitre att&ck framework

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:39.670134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:35.559459Z digest=sha256:9c601be6ebaea6558e23d2a4b92ac9bcfe30d4fbbbf2c21fd73190d30368b271

Observation f1af6ce6-4357-47cb-b362-845b30d05d0c · outbound

This paper cites an unresolved cited work.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Unresolved cited work

Reference 27

Resolution
unresolved
raw_fallback, observed 2026-08-06T01:04:39.477940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:35.686760Z digest=sha256:8c5e8b98092713d9a91bf1070309ae76a7c913e16c7a10e15853f62cb02d42c6

Observation 01b5026a-5df5-43e8-aa8b-ec06fd20e426 · outbound

This paper cites Safety alignment should be made more than just a few tokens deep.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Safety alignment should be made more than just a few tokens deep

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:39.273006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:35.868831Z digest=sha256:9923683a09a2ec745c18e560758ed2428c0f0918e351ff5368fce0775258606e

Observation 208f0a86-45a1-4752-810c-4519b7b9c8e3 · outbound

This paper cites Derail yourself: Multi-turn llm jailbreak attack through self-discovered clues.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Derail yourself: Multi-turn llm jailbreak attack through self-discovered clues

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:36.036452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:36.036452Z digest=sha256:df38422f492ce44e97af90201d77f3794784e88c7c3b654ee2ea2361a211904f

Observation c6edaf89-f599-4ad1-be58-872ed85b09bb · outbound

This paper cites Amazon nova ai challenge, trusted ai: Advancing secure, ai-assisted software development.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Amazon nova ai challenge, trusted ai: Advancing secure, ai-assisted software development

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:36.203876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:36.203876Z digest=sha256:2eed3d547c61375fa1ab7d339cbb1e45eaa37171e8d66d4383801128ffc1a17d

Observation 6dbccbd1-c913-4925-85b4-3920db2a1035 · outbound

This paper cites PAL: Proxy-Guided Black-Box Attack on Large Language Models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants PAL: Proxy-Guided Black-Box Attack on Large Language Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:36.335715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:36.335715Z digest=sha256:88609ac1380b55ec394ec4f2a27644f6d73444f36febd360c46e8f2ddeb5588a

Observation 51cd24be-ffca-475b-990c-f28d38ff6105 · outbound

This paper cites All in how you ask for it: Simple black-box method for jailbreak attacks.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants All in how you ask for it: Simple black-box method for jailbreak attacks

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:39.088687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:36.455952Z digest=sha256:5788bc04205ec845085019d69cdbc584fd88171af29fe47aedb8b5a23bb4524a

Observation 3920e8cc-265d-4ca6-98df-45a10e33d5c0 · outbound

This paper cites Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:36.652798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:36.652798Z digest=sha256:ebd93c8c5ffb0e458846f72428e3c44a3c8010b766a8477fab24f03922a5f395

Observation 346efe3b-459c-4312-9854-c9731512dcea · outbound

This paper cites ProSec: Fortifying Code LLMs with Proactive Security Alignment.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants ProSec: Fortifying Code LLMs with Proactive Security Alignment

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:36.818718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:36.818718Z digest=sha256:e43717daf8e38d440f3f60aa9ff1c112541a069ba487367f9af12b98c7e90fcc

Observation 0bd91f19-cf02-421f-bbc0-8f9bb06b0190 · outbound

This paper cites Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:36.972190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:36.972190Z digest=sha256:339637cff9ae13d19602a3b60db3e288cb8027163f76a819db4b7b06c9ed6279

Observation e98005c7-8d0e-4489-99a6-77ecb1d48d54 · outbound

This paper cites Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:37.095430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:37.095430Z digest=sha256:e1b674236999d96563bf9e6e1a4f94e9a6483bb7d87be3281d9118ebe15acc0d

Observation ac7a9035-07ae-430b-b641-60910a5a391f · outbound

This paper cites Fuzzllm: A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Fuzzllm: A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:38.829190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:37.196858Z digest=sha256:c65434aadea3867d5e2228479208e9d73fdfc533a3b1dfcd4c3b394a449f417e

Observation 6c70e40f-474d-43cd-a962-a7b3e4982530 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:37.329174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:37.329174Z digest=sha256:49f3a6a7794a58a2bc007b55daa597fb5c00ba11d23c26afccdba8995000ec16

Observation 6810af61-636b-44b5-b793-83c251a7417c · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:38.628111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:37.472973Z digest=sha256:3a64071cdee4dba36ee46038851167ba82d7f7a9be49bc3d926d27bdeff0a4fe

Observation f5fdb5b4-8e62-4e54-8e83-2fbd263943e6 · outbound

This paper cites Make them spill the beans! coercive knowledge extraction from (production) llms, 2023.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Make them spill the beans! coercive knowledge extraction from (production) llms, 2023

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:37.599060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:37.599060Z digest=sha256:9b99ee070fd7f393efa535aa194a860f39200e4b4f3f8bab3801c4c194dbb7de

Observation a6090ed3-68bf-4172-90a9-75e8f966bba4 · outbound

This paper cites Improving llm safety alignment with dual-objective optimization.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Improving llm safety alignment with dual-objective optimization

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T01:04:37.662594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T01:04:37.662594Z digest=sha256:1242bea272c03c24e5039785b4d6d3c41627409b9b0b79eb2673881dec8e1367

Observation 51c43beb-462a-4e2d-bac6-c2dc4263f8d3 · outbound

This paper cites Improving alignment and robustness with circuit breakers.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Improving alignment and robustness with circuit breakers

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:04:38.425658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-06T01:04:37.815257Z digest=sha256:2a2a5c997a27a398135317d679e4216e1efd2693bbb2ad7cb49ab5b555bcd0e4

Pith citing papers

Observation 7e1cff52-ceed-41bd-8e65-b0338c7494c1 · inbound

Reasoning Up the Instruction Ladder for Controllable Language Models cites this paper.

Reasoning Up the Instruction Ladder for Controllable Language Models ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-04T07:07:56.502297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T07:07:56.502297Z digest=sha256:6a68e680387e121ea5e0514f3868cb7640c1bb202a3087fff44901683b4819e0

Observation c184f991-9329-4fa6-a5e8-7c3357a9d2c4 · inbound

Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study cites this paper.

Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Reference 70

Resolution
verified exact
arxiv_id, observed 2026-05-17T03:38:57.937923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-17T03:38:40.078229Z digest=sha256:63be735c25bf40bbb51312eb271297054ba5e410c31b770f3f67351c51eda298

Observation f6d2e857-42e4-467e-9005-c534349c8a4b · inbound

Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025) cites this paper.

Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025) ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-05-21T07:39:48.564700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-21T07:38:43.363709Z digest=sha256:fde3662b7694701f93413701fc86b6c69dec1a18bfcfe7bd1354cc79ef2b3802

Observation 37b79c2f-6957-4463-b664-759dc1b693ab · inbound

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests cites this paper.

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-06-29T11:33:22.653764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-06-29T11:31:10.407386Z digest=sha256:d05513785115382f01ed416fb8cb2e9ffe280adc16b30f6e889fa6c8785dcf2c