Over the past few years, machine learning has been widely utilized to enhance cybersecurity. In this talk, we will present two of our recent projects in this area: the use of autoencoders to defend against adversarial attacks and the detection of darknet traffic over Tor. In the first project, we observed that machine learning-based intrusion detection systems (IDSs) have become increasingly popular due to their strong detection capability and adaptability.

My research asks a fundamental question: how does the immune system communicate with the brain, and how does the brain respond? These neuroimmune interactions shape behavior and survival during disease — most visibly in sickness, when animals stop eating, lose motivation, and withdraw from social contact. Unlike other sickness behaviors, social withdrawal is uniquely adaptive: it benefits both the sick individual and healthy members of the same group.

Precision oncology demands the integration of complementary data modalities, e.g., histopathology, spatial omics, and clinical records; yet current AI approaches rarely bridge them at scale. This talk presents a multimodal foundation AI program built around that integration. H&E-stained slides occupy a privileged role in this framework: universally collected as standard of care, they serve as the translational anchor through which spatially resolved molecular information can be delivered to patients who will never have access to high-plex assays. The program spans three AI capabilities: vision-language foundation models (MUSK, Nature 2025;

多模态多组学的高通量测序数据，从基因测序到蛋白质测序，到单细胞测序，再到空间组学，高通量测序的数据为训练深度学习的基础模型带来了可能。基于生命科学领域海量高通量数据的基础模型也为科学研究带来了新的研发范式，如何布局生命科学领域的大模型，如何用AI驱动的流程构建基于发现，理性设计和高通量实验验证的闭环方案，进而在临床以及虚拟细胞方向能够应用，百图生科用5年多的实践给出自己的体会和经验。

5月29日，SYSH Hub Forum第九场学术论坛在香港科技大学（广州）E1-101顺利举办。本次论坛聚焦环境医学、皮肤病学、暴露组学与衰老生物学交叉前沿，特邀德国国家科学院院士、德国莱布尼茨环境医学研究所（IUF）所长Jean Krutmann教授作了题为《皮肤衰老及相关疾病：从暴露组学和早衰样模型系统到预防与管理的转化策略》的前沿学术讲座。

Every time we reach for a drink, tap on our phone, or button a shirt, the brain coordinates dozens of limb muscles with remarkable speed and precision. These movements depend not on a simple one-way command from brain to body, but on a continuous sensorimotor loop in which descending signals drive movement while sensory feedback updates the brain about the body’s evolving state.

What does it feel like to cross the road in front of a car with no driver? Or to watch a delivery robot get stuck on a footpath and wonder “do I help”? This presentation takes these everyday encounters seriously. Drawing on research in autonomous vehicles–pedestrian interaction and human–robot collaboration, we explore how pedestrians and bystanders navigate a world increasingly shared with autonomous systems, and what design research can do to make those interactions feel more natural, legible, and human.

SYSH Hub Forum是面向系统枢纽专业的高层次学术论坛，旨在邀请相关领域内的顶尖专家与具有影响力的学者分享研究、经验和成果，聚焦学术前沿研究，加强交流与合作。SYSH Hub Forum 每季度举办一次，于2024年春季首发。每次的主讲嘉宾由系统枢纽其中一个学域提名，被提名人必须是该领域内国际公认的专家学者，由院长和学域主任投票同意后进行邀请。

作为一道屏障器官，皮肤是研究环境诱导（外源性）皮肤衰老的理想模型。本次讲座，Krutmann教授将阐述外源性皮肤老化的发生机制，包括皮肤暴露于特定暴露组因素所产生的后果、这些因素之间的相互作用、遗传因素对它们皮肤效应的调节，以及如何将这些发现成功转化为用于皮肤防护的化妆品与营养策略的开发。他还将讨论近期的机制研究，即利用核苷酸切除修复综合征中的科凯恩氏综合症B（CSB）和着色性干皮病A（XPA）作为加速模型来研究外源性皮肤衰老。这些研究揭示了CSB和XPA蛋白除了在核苷酸切除修复中的已知功能外，还具有此前未知的生物学作用。例如，通过使用CSB缺陷的人成纤维细胞、秀丽隐杆线虫和小鼠模型，研究证明CSB能够促进α-微管蛋白的乙酰化，从而调控自噬。具体而言，CSB与组蛋白乙酰化酶6以及α-微管蛋白乙酰转移酶MEC-17直接相互作用。

Autonomous Vehicle (AV) technology holds the promise of transforming future transportation systems, but its large-scale deployment requires rigorous safety evaluation. To address this need, we propose a behavioral safety assessment program to evaluate AV driving intelligence, consisting of two key components: (1) high-fidelity simulations that replicate real-world driving conditions, and (2) efficient testing strategies to accelerate validation. Central to this is modeling a Naturalistic Driving Environment (NDE) with distribution-level accuracy. We develop a deep learning-based framework to simulate statistically realistic human driving behavior, particularly for those long-tail safety-critical events. However, directly testing in the NDE is inefficient due to the rarity of such events. To address this, we introduce the Naturalistic and Adversarial Driving Environment (NADE), reducing test mileage without sacrificing accuracy. The proposed AV behavioral safety assessment program has been successfully deployed at physical testing facilities for real-world AV evaluation.