大会

大会

---

AAAI

2021年度AAAI国际人工智能会议线上举行。本届大会主席首次由华人（香港科技大学讲席教授、微众银行首席人工智能官杨强教授）担任。

如何进一步提升模型的鲁棒性以对抗潜在的攻击、如何充分保护数据私隐降低泄露风险、如何提升模型的计算效率降低对计算资源的需求，是亟待解决的三大热点问题。期间的国际研讨会（AAAI 2021 Workshop | L）主要包括三场主题演讲，交流话题包括：对抗学习、训练数据下毒和对抗学习、私隐保护机器学习的应用、分布式训练中信息交换效率的提高、模型压缩、模型鲁棒性等。

Topic of Interests

Theoretical contributions of adversarial machine learning.
Training data poisoning and adversarial learning.
Adversarial attacks(e.g. evation) and defenses.
Secure machine learning.
Privacy-preserving machine learning.
Application of privacy-preserving machine learning.
Privacy attacks such as membership inference, and model inversion.
Secure multi-party computation.
Model compression and efficiency improvement in both training and inference.
Efficiency improvement of information exchange in distributed training.
Model robustness against model compression.

---

2022 AAAI 入选论文：亚洲微软研究院 | 成都信息工程大学

2023 AAAI 2023实用AI挑战赛

---

---