Demo Data from SIGIR 2026 / reviewers in the wild / expert
Ngoc N. Tran
dblp:259/8194
· DBLP profile ↗
3ranked-venue papers
0as first author
3since 2021 · last 2025
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 2 · 2 since 2021Graphics, computer vision, multimedia, augmented reality and games · 2 · 2 since 2021Security and privacy · 1 · 1 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
2 papers |
Learning theory · 36% Generative modeling · 28% Learning paradigms · 18% | |
| Network and information security
2 papers |
Security and privacy of machine learning · 68% Privacy and data protection · 24% Malware analysis · 7% |
Topics — the 11 heaviest of 12, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Learning theory
generalization bounds |
0.9 | 1 | 2025 | Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective · ICCV 2025 |
Machine learning › Deep learning architectures and training › loss function design
loss weighting |
0.9 | 1 | 2025 | Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective · ICCV 2025 |
Machine learning › Learning theory › generalization
multi-task generalization |
0.9 | 1 | 2025 | Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective · ICCV 2025 |
Machine learning › Learning paradigms
multi-task learning |
0.9 | 1 | 2025 | Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective · ICCV 2025 |
Security and privacy of machine learning › adversarial attack › backdoor attack
backdoor defense |
0.9 | 1 | 2025 | PBP: Post-training Backdoor Purification for Malware Classifiers · NDSS 2025 |
Security and privacy of machine learning › adversarial attack › backdoor attack › backdoor defense
backdoor removal |
0.9 | 1 | 2025 | PBP: Post-training Backdoor Purification for Malware Classifiers · NDSS 2025 |
Machine learning › Generative modeling
diffusion model |
0.7 | 1 | 2023 | Anti-DreamBooth: Protecting users from personalized text-to-image synthesis · ICCV 2023 |
Machine learning › Generative modeling › diffusion model
text-to-image generation |
0.7 | 1 | 2023 | Anti-DreamBooth: Protecting users from personalized text-to-image synthesis · ICCV 2023 |
Security and privacy of machine learning › adversarial attack
adversarial perturbation |
0.7 | 1 | 2023 | Anti-DreamBooth: Protecting users from personalized text-to-image synthesis · ICCV 2023 |
Privacy and data protection › web privacy › online advertising privacy
anti-personalization defense |
0.7 | 1 | 2023 | Anti-DreamBooth: Protecting users from personalized text-to-image synthesis · ICCV 2023 |
Privacy and data protection
image privacy |
0.2 | 1 | 2023 | Anti-DreamBooth: Protecting users from personalized text-to-image synthesis · ICCV 2023 |
Methods — techniques the papers use, named apart from their topics
perturbation optimization · 1.3adversarial noise · 1.3post-training purification · 0.9generalization theory · 0.9
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
Hoang Phan, Lam Tran, Quyen Tran, Ngoc N. Tran, Tuan Truong, Nhat Ho, Dinh Q. Phung, Trung Le 0001 |
ICCV | 4 |
| 2025 | PBP: Post-training Backdoor Purification for Malware Classifiers
Dung Thuy Nguyen, Ngoc N. Tran, Taylor T. Johnson, Kevin Leach |
NDSS | 2 |
| 2023 | Anti-DreamBooth: Protecting users from personalized text-to-image synthesisabstractText-to-image diffusion models are nothing but a revolution, allowing anyone, even without design skills, to create realistic images from simple text inputs. With powerful personalization tools like DreamBooth, they can generate images of a specific person just by learning from his/her few reference images. However, when misused, such a powerful and convenient tool can produce fake news or disturbing content targeting any individual victim, posing a severe negative social impact. In this paper, we explore a defense system called Anti-DreamBooth against such malicious use of DreamBooth. The system aims to add subtle noise perturbation to each user’s image before publishing in order to disrupt the generation quality of any DreamBooth model trained on these perturbed images. We investigate a wide range of algorithms for perturbation optimization and extensively evaluate them on two facial datasets over various text-to-image model versions. Despite the complicated formulation of Dream-Booth and Diffusion-based text-to-image models, our methods effectively defend users from the malicious use of those models. Their effectiveness withstands even adverse conditions, such as model or prompt/term mismatching between training and testing. Our code will be available at https://github.com/VinAIResearch/Anti-DreamBooth.git. Thanh Van Le, Hao Phung, Thuan Hoang Nguyen, Quan Dao, Ngoc N. Tran, Anh Tuan Tran 0001 |
ICCV | 5 |