EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Evaluating Bias In The Creation and Perception of GAN-Generated Faces
EAGER:DCL:SaTC:实现跨学科协作:评估 GAN 生成的面孔的创建和感知中的偏差
基本信息
- 批准号:2210142
- 负责人:
- 金额:$ 29.63万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-07-01 至 2025-06-30
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Bad actors often use bots and fake profiles to attack individuals or groups and to undermine social harmony and collective movements. These fake profiles may use face images to signal human authenticity. Until recently it was possible to identify bad-faith actors via reverse image searches because many fake profiles used stock photos. Recent advances in machine learning-enabled general adversarial networks (GANs) have made it possible to create hyper-realistic faces of people who do not exist and cannot be identified. These faces can be animated and used to cause harm. To help develop more secure and trustworthy cyberspaces, it is critical to understand whether and how human perceivers (alone or with computational aids) can detect real vs. artificial faces, and how their detection strategies and outcomes differ across groups. This project investigates whether the GANs that generate faces are racially biased and whether this bias is manifested in differential detectability of ingroup vs. outgroup faces. The project tests the hypothesis that GANs are racially biased because the training dataset is itself biased, with White faces (especially White female faces) overrepresented. Furthermore, when tools are created to control what kind of face is generated, these tools may be racially biased as well because they are extracting biased parameters. These biased processes may result in GAN-generated faces that are more detectable to racial minority individuals vs. racial majority individuals. To test these hypotheses, the project is developing a training dataset of diverse faces, with annotations for dimensions of interest such as skin tone and gender. These annotations can be used to train a GAN with any number of checkpoints to examine how GAN-generated faces appear at different stages of creation. The project is examining how people perceive the generated faces at each stage of the GAN. This project is helping spur theoretical insights into how machine-learning works, and provides training in computer science and social psychology for a diverse group of undergraduate researchers.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
不良行为者经常使用机器人和虚假个人资料来攻击个人或团体,破坏社会和谐和集体运动。这些虚假的个人资料可能使用面部图像来表示人类的真实性。直到最近,人们才有可能通过反向图像搜索来识别恶意行为者,因为许多虚假的个人资料都使用了库存照片。支持机器学习的通用对抗网络(GAN)的最新进展使得创建不存在且无法识别的人的超现实面孔成为可能。这些脸可以被动画化并用来造成伤害。为了帮助开发更安全、更值得信赖的网络空间,关键是要了解人类感知者(单独或借助计算辅助)是否以及如何检测到真实的面孔和人造面孔,以及他们的检测策略和结果在不同群体中有何不同。该项目研究生成人脸的GAN是否存在种族偏见,以及这种偏见是否表现在内组与外组人脸的差异检测能力上。该项目测试了GAN存在种族偏见的假设,因为训练数据集本身就存在偏见,白色面孔(尤其是白色女性面孔)的比例过高。此外,当创建工具来控制生成什么样的面部时,这些工具也可能具有种族偏见,因为它们提取了有偏见的参数。这些有偏见的过程可能会导致GAN生成的人脸更容易被少数种族个体检测到,而不是种族多数个体。为了验证这些假设,该项目正在开发一个不同面孔的训练数据集,并对肤色和性别等感兴趣的维度进行注释。这些注释可用于训练具有任意数量检查点的GAN,以检查GAN生成的面部在创建的不同阶段如何出现。该项目正在研究人们如何在GAN的每个阶段感知生成的面孔。该项目有助于激发对机器学习如何工作的理论见解,并为不同的本科生研究人员提供计算机科学和社会心理学方面的培训。该奖项反映了NSF的法定使命,并通过使用基金会的智力价值和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Alvin Grissom其他文献
Mitigating Racial Bias in Social Media Hate Speech Detection
减轻社交媒体仇恨言论检测中的种族偏见
- DOI:
- 发表时间:
2021 - 期刊:
- 影响因子:0
- 作者:
Jiangxue Han;Jane Chandlee;Amanda Payne;Alvin Grissom - 通讯作者:
Alvin Grissom
Alvin Grissom的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
相似国自然基金
OH+HCl/DCl↔H2O/HOD+Cl态-态反应的全维微分截面研究
- 批准号:
- 批准年份:2022
- 资助金额:54 万元
- 项目类别:面上项目
番茄抗病毒基因DCL2b受病毒诱导调控的分子机理
- 批准号:
- 批准年份:2022
- 资助金额:54 万元
- 项目类别:面上项目
套索RNA通过拮抗DCL1复合物抑制植物miRNA产生的分子机制
- 批准号:31671261
- 批准年份:2016
- 资助金额:63.0 万元
- 项目类别:面上项目
拟南芥DCL4介导、不依赖DRB4的新抗病毒RNA沉默分子机制研究
- 批准号:31570145
- 批准年份:2015
- 资助金额:66.0 万元
- 项目类别:面上项目
DCL在DNAmβ诱导的基因沉默和抗TYLCCNV病毒中的功能分析
- 批准号:30771406
- 批准年份:2007
- 资助金额:32.0 万元
- 项目类别:面上项目
相似海外基金
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Deplatforming and Online Hate Speech Across the Social Media Ecology
EAGER:DCL:SaTC:实现跨学科合作:社交媒体生态中的去平台化和在线仇恨言论
- 批准号:
2210023 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Using NLP to Identify Suspicious Transactions in Omnichannel Online C2C Marketplaces
EAGER:DCL:SaTC:实现跨学科协作:使用 NLP 识别全渠道在线 C2C 市场中的可疑交易
- 批准号:
2210091 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Efficient Human-in-the-Loop Redaction of Language Development Corpora
EAGER:DCL:SaTC:实现跨学科协作:语言开发语料库的高效人机交互编辑
- 批准号:
2210193 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Space Cybersecurity, Policy, and Risks
EAGER:DCL:SaTC:实现跨学科合作:空间网络安全、政策和风险
- 批准号:
2208458 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Adapting Economic Games to Personalize Privacy and Security Nudges
EAGER:DCL:SaTC:实现跨学科合作:调整经济游戏以个性化隐私和安全推动
- 批准号:
2209507 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Improving Human Discernment of Audio Deepfakes via Multi-level Information Augmentation
EAGER:DCL:SaTC:实现跨学科合作:通过多级信息增强提高人类对音频深赝品的识别能力
- 批准号:
2210011 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Inoculation vs. education: the role of real time alerts and end-user overconfidence
EAGER:DCL:SaTC:实现跨学科协作:接种与教育:实时警报和最终用户过度自信的作用
- 批准号:
2210198 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collab: Impact-aware Machine Learning for Fair and Private Decision Making: Algorithms and Applications in Juvenile Justice Systems
EAGER:DCL:SaTC:实现跨学科协作:影响感知机器学习促进公平和私人决策:少年司法系统中的算法和应用
- 批准号:
2209951 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Evolutionary Insights into Digital Ecologies of Fear
EAGER:DCL:SaTC:实现跨学科合作:对数字恐惧生态的进化洞察
- 批准号:
2210082 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant
EAGER: DCL: SaTC: EIC: Inclusive-ScamBuster: Inclusive Scam Detection Methods for Social Media to Design Assistive Tools for Protecting Individuals with Developmental Disabilities
EAGER:DCL:SaTC:EIC:Inclusive-ScamBuster:社交媒体的包容性诈骗检测方法,用于设计保护发育障碍人士的辅助工具
- 批准号:
2210107 - 财政年份:2022
- 资助金额:
$ 29.63万 - 项目类别:
Standard Grant