CAREER: Towards Fairness in the Real World under Generalization, Privacy and Robustness Challenges

职业：在泛化、隐私和稳健性挑战下实现现实世界的公平

• 批准号: 2339198
• 负责人: Kai Shu
• 金额: $ 49.98万
• 依托单位: Illinois Institute of Technology
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-04-15 至 2029-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2339198&HistoricalAwards=false
• 关键词: CAREER; Towards; Fairness; Real; World

Artificial Intelligence (AI) algorithms are widely adopted in various real-world applications such as social media mining and health informatics. It becomes increasingly essential to ensure fairness in AI algorithms to avoid amplifying inequalities and reinforcing existing prejudice. Although fairness algorithms have achieved great progress recently, when deployed in the real world, they still face practical generalization, privacy and robustness challenges. First, the fairness performance can be significantly degraded under distribution shifts such as domain and temporal shifts. Second, most previous fairness algorithms require direct access to the exact demographic attributes, which is usually infeasible due to people's awareness and legal regulations on privacy. Moreover, research indicates that addressing fairness may increase privacy leakage risks. Third, malicious actors can amplify the demographic bias of AI algorithms by injecting poisoning samples in the training stage or manipulating the data in the inference stage. The goal of this project is to investigate the impact of the aforementioned issues on fairness and develop effective solutions to ensure fairness under generalization, privacy and robustness challenges.To achieve the research goal, the project systematically investigates the key directions of fairness under domain and temporal shifts, fairness faced with privacy mechanism enforcement and privacy leakage risks, bias amplification attack and defense methods. The project outcomes help advance state-of-the-art research on fair AI and introduce: (1) fairness in domain adaptation from an information-theoretical perspective and a meta-learning framework to ensure temporal-invariant fairness; (2) algorithms improving fairness performance under local differential privacy mechanism and achieving fair graph learning while minimizing the privacy leakage; and (3) poisoning and evasion attacks on fairness properties, as well as model-centric and data-centric defense methods for such attacks accordingly. More broadly, this project will have an immediate and strong impact on improving fairness algorithms in practices, enabling the responsible data analysis with advanced trustworthy AI paradigms in the real world.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.

人工智能（AI）算法广泛应用于社交媒体挖掘和健康信息学等各种现实应用中。确保人工智能算法的公平性以避免扩大不平等和强化现有偏见变得越来越重要。尽管公平算法最近取得了巨大进步，但在现实世界中部署时，它们仍然面临着实际的泛化、隐私和鲁棒性方面的挑战。首先，在分布变化（例如域和时间变化）下，公平性性能可能会显着下降。其次，之前的大多数公平算法都需要直接访问准确的人口统计属性，但由于人们的隐私意识和法律规定，这通常是不可行的。此外，研究表明，解决公平性可能会增加隐私泄露风险。第三，恶意行为者可以通过在训练阶段注入中毒样本或在推理阶段操纵数据来放大人工智能算法的人口统计偏差。本项目的目标是调查上述问题对公平性的影响，并制定有效的解决方案，以确保泛化、隐私和鲁棒性挑战下的公平性。为了实现研究目标，该项目系统地研究了域和时态下公平性的关键方向变化、隐私机制执行面临的公平性和隐私泄露风险、偏差放大攻击和防御方法。该项目成果有助于推进公平人工智能的最先进研究，并引入：（1）从信息理论角度和元学习框架确保领域适应的公平性，以确保时间不变的公平性； （2）算法提高局部差分隐私机制下的公平性，实现公平的图学习，同时最大限度地减少隐私泄露； (3)针对公平性的投毒和规避攻击，以及针对此类攻击的相应的以模型为中心和以数据为中心的防御方法。更广泛地说，该项目将对改进实践中的公平算法产生直接而强烈的影响，从而在现实世界中利用先进的、值得信赖的人工智能范例实现负责任的数据分析。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。