Monday, July 14, 2025

Previous | Next

• Geoffrey Fong inducted into Canadian Medical Hall of Fame
• Recognizing donors with care and craft
• Research team wins Best Paper award at CODASPY 2025

 Geoffrey Fong inducted into the Canadian Medical Hall of Fame

Dr. Fong addresses the audience at the CMHF event.

A message from the Office of Research.

Recently, Dr. Geoffrey Fong, professor in the Department of Psychology, was inducted into the Canadian Medical Hall of Fame (CMHF) at a ceremony held in association with McMaster University on June 19. CMHF recognizes Canadian health professionals whose work advances health in Canada and the world and develops the next generation of health professionals through the delivery of local and national youth education programs and awards.

Dr. Fong is a leading social psychologist who founded the International Tobacco Control Policy Evaluation Project (ITC Project) to assess the impact of tobacco control policies, including smoke-free laws, tobacco taxes, and restrictions on tobacco advertising. The ITC Project is renowned for its scientific rigour and scope, having conducted studies in 31 countries, covering half the world's population, over the past two decades.

The ITC Project has also been responsive to emerging tobacco use trends and now conducts research on new nicotine products like e-cigarettes and nicotine pouches. “We are studying whether e-cigarettes help those who smoke to quit,” Dr. Fong said, “but we have also started a multi-country youth survey to study vaping among youth who are at risk of becoming addicted to vaping.” His findings will be important, as Health Canada continues to monitor the public health impact of vaping products, which are currently sold in eye-catching packaging.

Through his highly impactful research and advocacy, Dr. Fong has made Canada a world leader in the fight against tobacco, improving the health of many millions. Tobacco smoking remains the leading preventable cause of death in Canada and globally. You can read more about Dr. Fong’s work and achievements on the CMHF website.

Recognizing donors with care and craft

A message from Creative Studio.

This spring, Math Advancement partnered with Creative Studio to elevate how we thank and steward our donors. Together, we developed a suite of custom InDesign templates — from scholarship updates to research highlights — designed to help us share the impact of donor gifts with clarity, care, and polish. 

One standout example: a beautifully crafted update for major supporters of the William Tutte Scholarships, celebrating his recent recognition on a commemorative postage stamp. Royal Mail honoured Dr. William T. Tutte — a pioneer in combinatorics and WWII codebreaking hero — with a stamp marking the 80^th anniversary of V-E Day. “The custom template helped us deliver a meaningful, beautifully presented update,” says Christina Young, Donor Relations Officer. “We’ve already received great feedback from our faculty.”

 P.S. Love a good shortcut? Check out the growing library of ready-made templates on the Waterloo Brand site. And if you’ve got something more custom in mind, Creative Studio’s always game to collaborate.

Research team wins Best Paper award at CODASPY 2025

Vasisht Duddu, Anudeep Das, N. Asokan. Rui Zhang was unavailable for the photo.

This article was originally published on the Cheriton School of Computer Science website.

Anudeep Das, Vasisht Duddu, Rui Zhang and N. Asokan have received the Best Paper Award at CODASPY 2025, the 15^th ACM Conference on Data and Application Security and Privacy. Their paper, Espresso: Robust Concept Filtering in Text-to-Image Models, introduces a new technique to improve the effectiveness, safety and reliability of generative AI systems that create images from natural language text prompts.

“Congrats to the team,” said Raouf Boutaba, University Professor and Director of the Cheriton School of Computer Science. “Text-to-image generative AI models have many creative uses, but they also raise significant concerns. The research Anudeep, Vasisht, Rui and Asokan have conducted adds to the growing body of work to help ensure these models are not misused and abused.”

Anudeep Das is pursuing a master’s degree at the Cheriton School of Computer Science, advised by Professor N. Asokan. He works on analyzing and enhancing the security, privacy and fairness of generative AI systems. His primary research has been on securing image-generative diffusion models, and he plans on diving into the safety of large language models next. The Espresso project originated while Anudeep was an undergraduate research assistant with Professor Asokan, where he led both the initial research concept and paper development.

Vasisht Duddu is pursuing a PhD at the Cheriton School of Computer Science, also advised by Professor N. Asokan. His research focuses on risks to security, privacy, fairness and transparency in machine learning models. He also designs attacks to exploit these risks and defences to counter them to better understand the interplay between risks and defences. Additionally, he works on ensuring accountability in machine learning pipelines to meet regulatory requirements.

Professor N. Asokan is a Cheriton Chair at the Cheriton School of Computer Science and serves as the Executive Director of Waterloo’s Cybersecurity and Privacy Institute. His primary research theme is systems security broadly, including topics like developing and using novel platform security features, applying cryptographic techniques to design secure protocols for distributed systems, applying machine learning techniques to security and privacy problems, and understanding and addressing the security and privacy of machine learning applications themselves.

Rui Zhang is pursuing a PhD in Mathematics at Zhejiang University. He was a visiting doctoral student in Professor N. Asokan’s Secure Systems Group from August 2023 to August 2024. His research focuses on security in artificial intelligence, particularly concerning federated learning, intellectual property protection for machine learning models and data, and the robustness of DNN models. He develops both theoretical foundations and practical methods to analyze vulnerabilities and build defences to enhance the reliability of AI systems.

About this award-winning research

Diffusion-based text-to-image models are a type of generative AI system that produces high-quality images from text prompts. As these models are trained on large, unfiltered datasets scraped from the Internet, they can unintentionally create inappropriate content, including copyrighted material, violent images, and sensitive or explicit imagery. Because of their large capacity, these models can also memorize specific concepts, which can reappear in generated images.

Previous efforts to remove inappropriate content, using what are known as concept removal techniques, or CRTs, have been unable to satisfy three important requirements simultaneously — effectiveness in filtering unacceptable concepts, utility in preserving the ability to generate acceptable and desirable content, and robustness against adversarial prompts to evade filters.

To address this challenge, the research team developed Espresso, a novel and robust content filter that uses a contrastive language-image pre-training model that meets all requirements simultaneously. Unlike earlier methods, which either modified the underlying text-to-image generator or used less adaptable classifiers, Espresso evaluates the distance between generated image embeddings and the text embeddings of both acceptable and unacceptable concepts. By using this dual-reference approach, Espresso enables more precise filtering and allows the model to be more effective and robust while preserving its utility.

The research team also conducted a comprehensive evaluation — a complete pipeline to comparatively evaluate various CRTs — demonstrating that Espresso outperforms seven fine-tuning-based CRTs and one filtering-based CRT on effectiveness, utility and resistance to adversarial attacks. Importantly, the researchers introduce the first approach to evaluate the robustness of CRTs, including defences against sophisticated adversarial prompts. Their results show that Espresso provides a better trade-off across effectiveness, utility and robustness compared with other state-of-the-art techniques.

To learn more about the award-winning research on which this article is based, please see Espresso: Robust Concept Filtering in Text-to-Image Models. Anudeep Das, Vasisht Duddu, Rui Zhang, N. Asokan. 2025. 15^th ACM Conference on Data and Application Security and Privacy (CODASPY).

You can also learn more about this research on the Secure Systems Group’s project page on content moderation for generative models.