Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step Article Swipe
Wenxuan Wang
,
Kun Gao
,
Zihan Jia
,
Youliang Yuan
,
Jen-tse Huang
,
Qiancheng Liu
,
Shuai Wang
,
Wenxiang Jiao
,
Zhaopeng Tu
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.03869
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.03869
Text-based image generation models, such as Stable Diffusion and DALL-E 3, hold significant potential in content creation and publishing workflows, making them the focus in recent years. Despite their remarkable capability to generate diverse and vivid images, considerable efforts are being made to prevent the generation of harmful content, such as abusive, violent, or pornographic material. To assess the safety of existing models, we introduce a novel jailbreaking method called Chain-of-Jailbreak (CoJ) attack, which compromises image generation models through a step-by-step editing process. Specifically, for malicious queries that cannot bypass the safeguards with a single prompt, we intentionally decompose the query into multiple sub-queries. The image generation models are then prompted to generate and iteratively edit images based on these sub-queries. To evaluate the effectiveness of our CoJ attack method, we constructed a comprehensive dataset, CoJ-Bench, encompassing nine safety scenarios, three types of editing operations, and three editing elements. Experiments on four widely-used image generation services provided by GPT-4V, GPT-4o, Gemini 1.5 and Gemini 1.5 Pro, demonstrate that our CoJ attack method can successfully bypass the safeguards of models for over 60% cases, which significantly outperforms other jailbreaking methods (i.e., 14%). Further, to enhance these models' safety against our CoJ attack method, we also propose an effective prompting-based method, Think Twice Prompting, that can successfully defend over 95% of CoJ attack. We release our dataset and code to facilitate the AI safety research.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2410.03869
- https://arxiv.org/pdf/2410.03869
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403928965
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403928965Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2410.03869Digital Object Identifier
- Title
-
Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by StepWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-04Full publication date if available
- Authors
-
Wenxuan Wang, Kun Gao, Zihan Jia, Youliang Yuan, Jen-tse Huang, Qiancheng Liu, Shuai Wang, Wenxiang Jiao, Zhaopeng TuList of authors in order
- Landing page
-
https://arxiv.org/abs/2410.03869Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2410.03869Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2410.03869Direct OA link when available
- Concepts
-
Image editing, Computer science, Image (mathematics), Two step, Computer graphics (images), Artificial intelligence, Chemistry, Combinatorial chemistryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403928965 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2410.03869 |
| ids.doi | https://doi.org/10.48550/arxiv.2410.03869 |
| ids.openalex | https://openalex.org/W4403928965 |
| fwci | |
| type | preprint |
| title | Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11689 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9911999702453613 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T12357 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9779000282287598 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Digital Media Forensic Detection |
| topics[2].id | https://openalex.org/T10775 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9509000182151794 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Generative Adversarial Networks and Image Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2776674983 |
| concepts[0].level | 3 |
| concepts[0].score | 0.6899261474609375 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q545981 |
| concepts[0].display_name | Image editing |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6045751571655273 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C115961682 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5867552757263184 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[2].display_name | Image (mathematics) |
| concepts[3].id | https://openalex.org/C3019136120 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5690595507621765 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2462428 |
| concepts[3].display_name | Two step |
| concepts[4].id | https://openalex.org/C121684516 |
| concepts[4].level | 1 |
| concepts[4].score | 0.33250725269317627 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7600677 |
| concepts[4].display_name | Computer graphics (images) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3229151964187622 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C185592680 |
| concepts[6].level | 0 |
| concepts[6].score | 0.16889432072639465 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[6].display_name | Chemistry |
| concepts[7].id | https://openalex.org/C21951064 |
| concepts[7].level | 1 |
| concepts[7].score | 0.1448618769645691 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q899212 |
| concepts[7].display_name | Combinatorial chemistry |
| keywords[0].id | https://openalex.org/keywords/image-editing |
| keywords[0].score | 0.6899261474609375 |
| keywords[0].display_name | Image editing |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6045751571655273 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/image |
| keywords[2].score | 0.5867552757263184 |
| keywords[2].display_name | Image (mathematics) |
| keywords[3].id | https://openalex.org/keywords/two-step |
| keywords[3].score | 0.5690595507621765 |
| keywords[3].display_name | Two step |
| keywords[4].id | https://openalex.org/keywords/computer-graphics |
| keywords[4].score | 0.33250725269317627 |
| keywords[4].display_name | Computer graphics (images) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.3229151964187622 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/chemistry |
| keywords[6].score | 0.16889432072639465 |
| keywords[6].display_name | Chemistry |
| keywords[7].id | https://openalex.org/keywords/combinatorial-chemistry |
| keywords[7].score | 0.1448618769645691 |
| keywords[7].display_name | Combinatorial chemistry |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2410.03869 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2410.03869 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2410.03869 |
| locations[1].id | doi:10.48550/arxiv.2410.03869 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2410.03869 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5106746626 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-9803-8204 |
| authorships[0].author.display_name | Wenxuan Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Wenxuan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5025793197 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3049-5086 |
| authorships[1].author.display_name | Kun Gao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gao, Kuiyi |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5075160383 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Zihan Jia |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Jia, Zihan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5101287548 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Youliang Yuan |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yuan, Youliang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5047584018 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-3446-0083 |
| authorships[4].author.display_name | Jen-tse Huang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Huang, Jen-tse |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5102776408 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Qiancheng Liu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Liu, Qiuzhi |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100328312 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-7897-2024 |
| authorships[6].author.display_name | Shuai Wang |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Wang, Shuai |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5023250445 |
| authorships[7].author.orcid | https://orcid.org/0000-0003-4951-9420 |
| authorships[7].author.display_name | Wenxiang Jiao |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Jiao, Wenxiang |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5110579339 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-7900-6055 |
| authorships[8].author.display_name | Zhaopeng Tu |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Tu, Zhaopeng |
| authorships[8].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2410.03869 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11689 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9911999702453613 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Adversarial Robustness in Machine Learning |
| related_works | https://openalex.org/W4319453795, https://openalex.org/W4205104112, https://openalex.org/W1974870326, https://openalex.org/W2770776392, https://openalex.org/W3176454756, https://openalex.org/W2772330423, https://openalex.org/W3163523050, https://openalex.org/W3006381446, https://openalex.org/W4386301887, https://openalex.org/W3015353979 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2410.03869 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2410.03869 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2410.03869 |
| primary_location.id | pmh:oai:arXiv.org:2410.03869 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2410.03869 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2410.03869 |
| publication_date | 2024-10-04 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 65, 79, 93, 132 |
| abstract_inverted_index.3, | 10 |
| abstract_inverted_index.AI | 230 |
| abstract_inverted_index.To | 56, 121 |
| abstract_inverted_index.We | 221 |
| abstract_inverted_index.an | 205 |
| abstract_inverted_index.as | 5, 50 |
| abstract_inverted_index.by | 157 |
| abstract_inverted_index.in | 14, 24 |
| abstract_inverted_index.of | 46, 60, 125, 142, 177, 218 |
| abstract_inverted_index.on | 118, 150 |
| abstract_inverted_index.or | 53 |
| abstract_inverted_index.to | 31, 42, 111, 192, 227 |
| abstract_inverted_index.we | 63, 96, 130, 202 |
| abstract_inverted_index.1.5 | 161, 164 |
| abstract_inverted_index.60% | 181 |
| abstract_inverted_index.95% | 217 |
| abstract_inverted_index.CoJ | 127, 169, 199, 219 |
| abstract_inverted_index.The | 104 |
| abstract_inverted_index.and | 8, 17, 34, 113, 145, 162, 225 |
| abstract_inverted_index.are | 39, 108 |
| abstract_inverted_index.can | 172, 213 |
| abstract_inverted_index.for | 84, 179 |
| abstract_inverted_index.our | 126, 168, 198, 223 |
| abstract_inverted_index.the | 22, 44, 58, 90, 99, 123, 175, 229 |
| abstract_inverted_index.Pro, | 165 |
| abstract_inverted_index.also | 203 |
| abstract_inverted_index.code | 226 |
| abstract_inverted_index.edit | 115 |
| abstract_inverted_index.four | 151 |
| abstract_inverted_index.hold | 11 |
| abstract_inverted_index.into | 101 |
| abstract_inverted_index.made | 41 |
| abstract_inverted_index.nine | 137 |
| abstract_inverted_index.over | 180, 216 |
| abstract_inverted_index.such | 4, 49 |
| abstract_inverted_index.that | 87, 167, 212 |
| abstract_inverted_index.them | 21 |
| abstract_inverted_index.then | 109 |
| abstract_inverted_index.with | 92 |
| abstract_inverted_index.(CoJ) | 71 |
| abstract_inverted_index.14%). | 190 |
| abstract_inverted_index.Think | 209 |
| abstract_inverted_index.Twice | 210 |
| abstract_inverted_index.based | 117 |
| abstract_inverted_index.being | 40 |
| abstract_inverted_index.focus | 23 |
| abstract_inverted_index.image | 1, 75, 105, 153 |
| abstract_inverted_index.novel | 66 |
| abstract_inverted_index.other | 186 |
| abstract_inverted_index.query | 100 |
| abstract_inverted_index.their | 28 |
| abstract_inverted_index.these | 119, 194 |
| abstract_inverted_index.three | 140, 146 |
| abstract_inverted_index.types | 141 |
| abstract_inverted_index.vivid | 35 |
| abstract_inverted_index.which | 73, 183 |
| abstract_inverted_index.(i.e., | 189 |
| abstract_inverted_index.DALL-E | 9 |
| abstract_inverted_index.Gemini | 160, 163 |
| abstract_inverted_index.Stable | 6 |
| abstract_inverted_index.assess | 57 |
| abstract_inverted_index.attack | 128, 170, 200 |
| abstract_inverted_index.bypass | 89, 174 |
| abstract_inverted_index.called | 69 |
| abstract_inverted_index.cannot | 88 |
| abstract_inverted_index.cases, | 182 |
| abstract_inverted_index.defend | 215 |
| abstract_inverted_index.images | 116 |
| abstract_inverted_index.making | 20 |
| abstract_inverted_index.method | 68, 171 |
| abstract_inverted_index.models | 77, 107, 178 |
| abstract_inverted_index.recent | 25 |
| abstract_inverted_index.safety | 59, 138, 196, 231 |
| abstract_inverted_index.single | 94 |
| abstract_inverted_index.years. | 26 |
| abstract_inverted_index.Despite | 27 |
| abstract_inverted_index.GPT-4V, | 158 |
| abstract_inverted_index.GPT-4o, | 159 |
| abstract_inverted_index.against | 197 |
| abstract_inverted_index.attack, | 72 |
| abstract_inverted_index.attack. | 220 |
| abstract_inverted_index.content | 15 |
| abstract_inverted_index.dataset | 224 |
| abstract_inverted_index.diverse | 33 |
| abstract_inverted_index.editing | 81, 143, 147 |
| abstract_inverted_index.efforts | 38 |
| abstract_inverted_index.enhance | 193 |
| abstract_inverted_index.harmful | 47 |
| abstract_inverted_index.images, | 36 |
| abstract_inverted_index.method, | 129, 201, 208 |
| abstract_inverted_index.methods | 188 |
| abstract_inverted_index.models' | 195 |
| abstract_inverted_index.models, | 3, 62 |
| abstract_inverted_index.prevent | 43 |
| abstract_inverted_index.prompt, | 95 |
| abstract_inverted_index.propose | 204 |
| abstract_inverted_index.queries | 86 |
| abstract_inverted_index.release | 222 |
| abstract_inverted_index.through | 78 |
| abstract_inverted_index.Further, | 191 |
| abstract_inverted_index.abusive, | 51 |
| abstract_inverted_index.content, | 48 |
| abstract_inverted_index.creation | 16 |
| abstract_inverted_index.dataset, | 134 |
| abstract_inverted_index.evaluate | 122 |
| abstract_inverted_index.existing | 61 |
| abstract_inverted_index.generate | 32, 112 |
| abstract_inverted_index.multiple | 102 |
| abstract_inverted_index.process. | 82 |
| abstract_inverted_index.prompted | 110 |
| abstract_inverted_index.provided | 156 |
| abstract_inverted_index.services | 155 |
| abstract_inverted_index.violent, | 52 |
| abstract_inverted_index.Diffusion | 7 |
| abstract_inverted_index.decompose | 98 |
| abstract_inverted_index.effective | 206 |
| abstract_inverted_index.elements. | 148 |
| abstract_inverted_index.introduce | 64 |
| abstract_inverted_index.malicious | 85 |
| abstract_inverted_index.material. | 55 |
| abstract_inverted_index.potential | 13 |
| abstract_inverted_index.research. | 232 |
| abstract_inverted_index.CoJ-Bench, | 135 |
| abstract_inverted_index.Prompting, | 211 |
| abstract_inverted_index.Text-based | 0 |
| abstract_inverted_index.capability | 30 |
| abstract_inverted_index.facilitate | 228 |
| abstract_inverted_index.generation | 2, 45, 76, 106, 154 |
| abstract_inverted_index.publishing | 18 |
| abstract_inverted_index.remarkable | 29 |
| abstract_inverted_index.safeguards | 91, 176 |
| abstract_inverted_index.scenarios, | 139 |
| abstract_inverted_index.workflows, | 19 |
| abstract_inverted_index.Experiments | 149 |
| abstract_inverted_index.compromises | 74 |
| abstract_inverted_index.constructed | 131 |
| abstract_inverted_index.demonstrate | 166 |
| abstract_inverted_index.iteratively | 114 |
| abstract_inverted_index.operations, | 144 |
| abstract_inverted_index.outperforms | 185 |
| abstract_inverted_index.significant | 12 |
| abstract_inverted_index.widely-used | 152 |
| abstract_inverted_index.considerable | 37 |
| abstract_inverted_index.encompassing | 136 |
| abstract_inverted_index.jailbreaking | 67, 187 |
| abstract_inverted_index.pornographic | 54 |
| abstract_inverted_index.step-by-step | 80 |
| abstract_inverted_index.sub-queries. | 103, 120 |
| abstract_inverted_index.successfully | 173, 214 |
| abstract_inverted_index.Specifically, | 83 |
| abstract_inverted_index.comprehensive | 133 |
| abstract_inverted_index.effectiveness | 124 |
| abstract_inverted_index.intentionally | 97 |
| abstract_inverted_index.significantly | 184 |
| abstract_inverted_index.prompting-based | 207 |
| abstract_inverted_index.Chain-of-Jailbreak | 70 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile |