Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation Article Swipe

PDF

Shuai Zhao , Xiaobao Wu , Cong-Duy Nguyen , Yanhao Jia , Meihuizi Jia , Feng Yichao , Anh Tuan Luu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.18653/v1/2025.findings-acl.255

Related Topics

Concepts

Backdoor Distillation Computer science Computer security Business Chemistry Organic chemistry

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.18653/v1/2025.findings-acl.255
PDF: https://aclanthology.org/2025.findings-acl.255.pdf
OA Status: gold
Cited By: 2
Related Works: 10
OpenAlex ID: https://openalex.org/W4412888737

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4412888737

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.18653/v1/2025.findings-acl.255

Digital Object Identifier
Title: Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-01-01

Full publication date if available
Authors: Shuai Zhao, Xiaobao Wu, Cong-Duy Nguyen, Yanhao Jia, Meihuizi Jia, Feng Yichao, Anh Tuan Luu

List of authors in order
Landing page: https://doi.org/10.18653/v1/2025.findings-acl.255

Publisher landing page
PDF URL: https://aclanthology.org/2025.findings-acl.255.pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://aclanthology.org/2025.findings-acl.255.pdf

Direct OA link when available
Concepts: Backdoor, Distillation, Computer science, Computer security, Business, Chemistry, Organic chemistry

Top concepts (fields/topics) attached by OpenAlex
Cited by: 2

Total citation count in OpenAlex
Citations by year (recent): 2025: 2

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4412888737
doi	https://doi.org/10.18653/v1/2025.findings-acl.255
ids.doi	https://doi.org/10.18653/v1/2025.findings-acl.255
ids.openalex	https://openalex.org/W4412888737
fwci	9.63949029
type	article
title	Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
biblio.issue
biblio.volume
biblio.last_page	4952
biblio.first_page	4937
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	0.98089998960495
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/T10237
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9272000193595886
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Cryptography and Data Security
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C2781045450
concepts[0].level	2
concepts[0].score	0.9725158214569092
concepts[0].wikidata	https://www.wikidata.org/wiki/Q254569
concepts[0].display_name	Backdoor
concepts[1].id	https://openalex.org/C204030448
concepts[1].level	2
concepts[1].score	0.5106959939002991
concepts[1].wikidata	https://www.wikidata.org/wiki/Q101017
concepts[1].display_name	Distillation
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.46429452300071716
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C38652104
concepts[3].level	1
concepts[3].score	0.4595346450805664
concepts[3].wikidata	https://www.wikidata.org/wiki/Q3510521
concepts[3].display_name	Computer security
concepts[4].id	https://openalex.org/C144133560
concepts[4].level	0
concepts[4].score	0.35975944995880127
concepts[4].wikidata	https://www.wikidata.org/wiki/Q4830453
concepts[4].display_name	Business
concepts[5].id	https://openalex.org/C185592680
concepts[5].level	0
concepts[5].score	0.1722402274608612
concepts[5].wikidata	https://www.wikidata.org/wiki/Q2329
concepts[5].display_name	Chemistry
concepts[6].id	https://openalex.org/C178790620
concepts[6].level	1
concepts[6].score	0.0
concepts[6].wikidata	https://www.wikidata.org/wiki/Q11351
concepts[6].display_name	Organic chemistry
keywords[0].id	https://openalex.org/keywords/backdoor
keywords[0].score	0.9725158214569092
keywords[0].display_name	Backdoor
keywords[1].id	https://openalex.org/keywords/distillation
keywords[1].score	0.5106959939002991
keywords[1].display_name	Distillation
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.46429452300071716
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/computer-security
keywords[3].score	0.4595346450805664
keywords[3].display_name	Computer security
keywords[4].id	https://openalex.org/keywords/business
keywords[4].score	0.35975944995880127
keywords[4].display_name	Business
keywords[5].id	https://openalex.org/keywords/chemistry
keywords[5].score	0.1722402274608612
keywords[5].display_name	Chemistry
language	en
locations[0].id	doi:10.18653/v1/2025.findings-acl.255
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by
locations[0].pdf_url	https://aclanthology.org/2025.findings-acl.255.pdf
locations[0].version	publishedVersion
locations[0].raw_type	proceedings-article
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Findings of the Association for Computational Linguistics: ACL 2025
locations[0].landing_page_url	https://doi.org/10.18653/v1/2025.findings-acl.255
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5034822677
authorships[0].author.orcid	https://orcid.org/0000-0001-5174-5182
authorships[0].author.display_name	Shuai Zhao
authorships[0].author_position	first
authorships[0].raw_author_name	Shuai Zhao
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5011376608
authorships[1].author.orcid	https://orcid.org/0000-0003-0076-3924
authorships[1].author.display_name	Xiaobao Wu
authorships[1].author_position	middle
authorships[1].raw_author_name	Xiaobao Wu
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5025645183
authorships[2].author.orcid	https://orcid.org/0000-0002-0931-460X
authorships[2].author.display_name	Cong-Duy Nguyen
authorships[2].author_position	middle
authorships[2].raw_author_name	Cong-Duy T Nguyen
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5119181472
authorships[3].author.orcid
authorships[3].author.display_name	Yanhao Jia
authorships[3].author_position	middle
authorships[3].raw_author_name	Yanhao Jia
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5024179471
authorships[4].author.orcid	https://orcid.org/0009-0003-5624-9980
authorships[4].author.display_name	Meihuizi Jia
authorships[4].author_position	middle
authorships[4].raw_author_name	Meihuizi Jia
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5116038830
authorships[5].author.orcid
authorships[5].author.display_name	Feng Yichao
authorships[5].author_position	middle
authorships[5].raw_author_name	Feng Yichao
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5050386762
authorships[6].author.orcid	https://orcid.org/0000-0002-1927-9895
authorships[6].author.display_name	Anh Tuan Luu
authorships[6].author_position	last
authorships[6].raw_author_name	Anh Tuan Luu
authorships[6].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://aclanthology.org/2025.findings-acl.255.pdf
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
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	0.98089998960495
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/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W4320031223, https://openalex.org/W4200629851, https://openalex.org/W4281902577, https://openalex.org/W4309417370, https://openalex.org/W4292107232, https://openalex.org/W3009072493, https://openalex.org/W4401407399
cited_by_count	2
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	2
locations_count	1
best_oa_location.id	doi:10.18653/v1/2025.findings-acl.255
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://aclanthology.org/2025.findings-acl.255.pdf
best_oa_location.version	publishedVersion
best_oa_location.raw_type	proceedings-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Findings of the Association for Computational Linguistics: ACL 2025
best_oa_location.landing_page_url	https://doi.org/10.18653/v1/2025.findings-acl.255
primary_location.id	doi:10.18653/v1/2025.findings-acl.255
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by
primary_location.pdf_url	https://aclanthology.org/2025.findings-acl.255.pdf
primary_location.version	publishedVersion
primary_location.raw_type	proceedings-article
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Findings of the Association for Computational Linguistics: ACL 2025
primary_location.landing_page_url	https://doi.org/10.18653/v1/2025.findings-acl.255
publication_date	2025-01-01
publication_year	2025
referenced_works_count	0
abstract_inverted_index
cited_by_percentile_year.max	97
cited_by_percentile_year.min	95
countries_distinct_count	0
institutions_distinct_count	7
citation_normalized_percentile.value	0.97805179
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True