Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Improving Translational Accuracy02:07

Improving Translational Accuracy

14.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.0K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.5K
3.5K
Survival Tree01:19

Survival Tree

369
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
369
RNA Editing02:23

RNA Editing

9.7K
RNA editing is a post-transcriptional modification where a precursor mRNA (pre-mRNA) nucleotide sequence is changed by base insertion, deletion, or modification. The extent of RNA editing varies from a few hundred bases, in mitochondrial DNA of trypanosomes, to a just single base, in nuclear genes of mammals. Even a single base change in the pre-mRNA can convert a codon for one amino acid into the codon for another amino acid or a stop codon. This type of re-coding can significantly affect the...
9.7K
Censoring Survival Data01:09

Censoring Survival Data

502
Survival analysis is a statistical method used to analyze time-to-event data, often employed in fields such as medicine, engineering, and social sciences. One of the key challenges in survival analysis is dealing with incomplete data, a phenomenon known as "censoring." Censoring occurs when the event of interest (such as death, relapse, or system failure) has not occurred for some individuals by the end of the study period or is otherwise unobservable, and it might have many different...
502
CRISPR01:59

CRISPR

57.4K
Genome editing technologies allow scientists to modify an organism’s DNA via the addition, removal, or rearrangement of genetic material at specific genomic locations. These types of techniques could potentially be used to cure genetic disorders such as hemophilia and sickle cell anemia. One popular and widely used DNA-editing research tool that could lead to safe and effective cures for genetic disorders is the CRISPR-Cas9 system. CRISPR-Cas9 stands for Clustered Regularly Interspaced...
57.4K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Regulatory insights underlying apple to cold stress.

Horticulture research·2026
Same author

Anorectal fibrosis in 3 murine models of chronic intestinal fibrosis: a comparative analysis.

Inflammatory bowel diseases·2026
Same author

Osimertinib Resistance in EGFR-Mutated Non-Small Cell Lung Cancer: Mechanisms and Therapeutic Strategies.

MedComm·2026
Same author

Kinetic Approach for Assessing Absolute Hydrogen Potential (pH<sub>abs</sub>) across Diverse Solvents.

The journal of physical chemistry. A·2026
Same author

Bronchovascular texture pattern on quantitative CT reveals airway and vascular remodeling in post-COVID-19 Lungs.

Respiratory research·2026
Same author

Algal δ<sup>13</sup>C reveals climate changes during the Cambrian Explosion.

Nature communications·2026

相关实验视频

Updated: Jan 8, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

986

几秒钟的后门:通过模型编辑解锁大型预训练模型中的漏洞

Dongliang Guo1, Mengxuan Hu1, Zihan Guan1

  • 1University of Virginia, Charlottesville, Virginia, USA.

Proceedings of the ... ACM International Conference on Information & Knowledge Management. ACM International Conference on Information and Knowledge Management
|December 17, 2025
PubMed
概括
此摘要是机器生成的。

研究人员开发了EDT,这是一种高效,无数据和无训练的后门攻击方法,用于大型预训练模型. 这种新的方法解决了攻击复杂的人工智能系统的挑战,而不需要训练数据或模型再训练.

关键词:
大型预训练模型模型编辑 模型编辑安全的安全的安全的安全的安全.

更多相关视频

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.2K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.2K

相关实验视频

Last Updated: Jan 8, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

986
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.2K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.2K

科学领域:

  • 人工智能的人工智能
  • 机器学习安全 机器学习安全
  • 计算机视觉 计算机视觉

背景情况:

  • 大型预训练模型 (例如,ViT) 强大,但易受后门攻击的影响.
  • 现有的攻击需要访问训练数据和大量的计算资源,这对大型模型构成挑战.

研究的目的:

  • 在大型预训练模型上调查后门攻击的独特挑战.
  • 开发一个有效和可行的后门攻击方法,适合这些模型.

主要方法:

  • 引入了EDT (高效,无数据,无培训),一种新的后门攻击方法.
  • 通过注入轻量级代码本来修改模型行为,而无需数据中毒或再培训,EDT利用模型编辑技术.

主要成果:

  • 在各种预训练模型 (ViT,CLIP,BLIP,稳定扩散) 中证明了EDT的有效性.
  • 在各种下游任务上验证了攻击的成功,例如图像分类,标题和生成.

结论:

  • 对于大型预训练模型的后门攻击,EDT提供了一个可行的解决方案,克服了以前的局限性.
  • 该方法提供了一种实际的方法来评估复杂的人工智能系统的脆弱性.