
Lingjuan
Lyu
Profile
Lingjuan is a senior research scientist and Privacy-Preserving Machine Learning (PPML) team leader in Sony AI. Prior to joining Sony AI, she spent more than six years working in academia and at industry research organizations. Lingjuan received her Ph.D. from the University of Melbourne. She was a recipient of the prestigious IBM PhD Fellowship Award in 2017, and has contributed to various professional activities, including ICML, NeurIPS, AAAI, IJCAI, and others. Lingjuan’s current research interests include federated learning, AI privacy and security, fairness, edge intelligence, and more. She has had more than 50 papers published in top conferences and journals, including NeurIPS, ICML, ICLR, Nature, AAAI, IJCAI, etc. Her papers have won numerous awards and have been selected as oral presentations at top conferences.
Message
“The Sony AI Privacy-Preserving Machine Learning (PPML) team conducts cutting-edge research on trustworthy AI. Our team aims to integrate more privacy-preserving and robust AI solutions across Sony products. In the long-term, I hope that we can make the industrial AI systems privacy-compliant and robust for social good.”
Publications
In recent years, knowledge graph~(KG) has obtained many achievements in both research and industrial fields. However, most KG algorithms consider node embedding with only structure and node features, but not relation features. In this paper, we propose a novel Heterogeneous …
Since training a large-scale backdoored model from scratch requires a large training dataset, several recent attacks have considered to inject backdoors into a trained clean model without altering model behaviors on the clean data. Previous work finds that backdoors can be i…
Adversarial training (AT) is a typical method to learn adversarially robust deep neural networks via training on the adversarial variants generated by their natural examples. However, as training progresses, the training data becomes less attackable, which may undermine the …
Federated learning is a privacy-preserving machine learning technique to train intelligent models from decentralized data, which enables exploiting private data by communicating local model updates in each iteration of model learning rather than the raw data. However, model …
Existing federated learning (FL) designs have been shown to exhibit vulnerabilities which can be exploited by adversaries to compromise data privacy. However, most current works conduct attacks by leveraging gradients calculated on a small batch of data. This setting is not …
Accurate traffic anomaly prediction offers an opportunity to save the wounded at the right location in time. However, the complex process of traffic anomaly is affected by both various static factors and dynamic interactions. The recent evolving representation learning provi…
Native ad is a popular type of online advertisement which has similar forms with the native content displayed on websites. Native ad CTR prediction is useful for improving user experience and platform revenue. However, it is challenging due to the lack of explicit user inten…
The fast growth of pre-trained models (PTMs) has brought natural language processing to a new era, which becomes a dominant technique for various natural language processing (NLP) applications. Every user can download weights of PTMs, then fine-tune the weights on a task on …
Federated learning (FL) provides a privacy-aware learning framework by enabling a multitude of participants to jointly construct models without collecting their private training data. However, federated learning has exhibited vulnerabilities to Byzantine attacks. Many existi…
Previous studies have shown that federated learning (FL) is vulnerable to well-crafted adversarial examples. Some recent efforts tried to combine adversarial training with FL, i.e., federated adversarial training (FAT), in order to achieve adversarial robustness in FL. Howev…
Cross Domain Recommendation (CDR) has been popularly studied to alleviate the cold-start and data sparsity problem commonly existed in recommender systems. CDR models can improve the recommendation performance of a target domain by leveraging the data of other source domains…
Visual surveillance technology is an indispensable functional component of advanced traffic management systems. It has been applied to perform traffic supervision tasks, such as object detection, tracking and recognition. However, adverse weather conditions, e.g., fog, haze …
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have been encapsulated in cloud APIs to serve over half a billion people worldwide and process over one hundred bil…
Social recommendation has shown promising improvements over traditional systems since it leverages social correlation data as an additional input. Most existing works assume that all data are available to the recommendation platform. However, in practice, user-item interacti…
Backdoor attack has emerged as a major security threat to deep neural networks(DNNs). While existing defense methods have demonstrated promising results on detecting and erasing backdoor triggers, it is still not clear if measures can be taken to avoid the triggers from bein…
Collaborative machine learning provides a promising framework for different agents to pool their resources (e.g., data) for a common learning task. In realistic settings where agents are self-interested and not altruistic, they may be unwilling to share data or model without…
Federated machine learning which enables resource-constrained node devices (e.g., Internet of Things (IoT) devices, smartphones) to establish a knowledge-shared model while keeping the raw data local, could provide privacy preservation and economic benefit by designing an ef…
Recently, large volumes of false or unverified information (e.g., fake news and rumors) appear frequently in emerging social media, which are often discussed on a large scale and widely disseminated, causing bad consequences. Many studies on rumor detection indicate that the…
Federated learning (FL) emerged as a promising learning paradigm to enable a multitude of partici- pants to construct a joint ML model without expos- ing their private training data. Existing FL designs have been shown to exhibit vulnerabilities which can be exploited by adv…
Blog

November 29, 2021 | Sony AI
Meet the Team #2: Lingjuan, Jerone and Roberto
What do privacy, pattern recognition, and percussion all have in common? They are concepts and creative endeavors that have inspired Sony AI team members Lingjuan, Jerone and Roberto. Read on to learn more about these three Sony…
What do privacy, pattern recognition, and percussion all have in common? They are concepts and creative endeavors that have insp…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.