Yi Yu

Yi Yu

Auto-generated profile, based on publicly available information

Yi Yu

Nanyang Technological University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2025 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
CKChenqi Kong
Chenqi Kong
ALAnwei Luo
Anwei Luo
PBPeijun Bao
Peijun Bao
YYYi Yu
Yi Yu
HLHaoliang Li
Haoliang Li
AKAlex C. Kot
Alex C. Kot
Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN-based face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance. However, these approaches still exhibit the following limitations: (1) Fully fine-tuning ViT-based models from ImageNet weights demands substantial computational and storage resources; (2) ViT-based methods struggle to capture local forgery clues, leading to model bias; (3) These methods limit their scope on only one or few face forgery features, resulting in limited generalizability. To tackle these challenges, this work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach. MoE-FFD only updates lightweight Low-Rank Adaptation (LoRA) and Adapter layers while keeping the ViT backbone frozen, thereby achieving parameter-efficient training. Moreover, MoE-FFD leverages the expressivity of transformers and local priors of CNNs to simultaneously extract global and local forgery clues. Additionally, novel MoE modules are designed to scale the model's capacity and smartly select optimal forgery experts, further enhancing forgery detection performance. Our proposed learning scheme can be seamlessly adapted to various transformer backbones in a plug-and-play manner. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art face forgery detection performance with significantly reduced parameter overhead in cross-dataset, cross-manipulation, and robustness evaluations. Our ablation studies further validate the effectiveness of the designed components and the proposed learning scheme. The code is available at: https://github.com/LoveSiameseCat/MoE-FFD.

26 May 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XLXun Lin
Xun Lin
ALAjian Liu
Ajian Liu
ZYZitong Yu
Zitong Yu
RCRizhao Cai
Rizhao Cai
SWShuai Wang
Shuai Wang
AKAlex Kot
Alex Kot
Face Anti-Spoofing (FAS) is essential for securing face recognition systems against presentation attacks. Recent advances in sensor technology and multimodal learning have enabled the development of multimodal FAS systems. However, existing methods often struggle to generalize to unseen attacks and diverse environments due to two key challenges: (1) Modality unreliability, where sensors such as depth and infrared suffer from severe domain shifts, impairing the reliability of cross-modal fusion; and (2) Modality imbalance, where over-reliance on a dominant modality weakens the model’s robustness against attacks that affect other modalities. To overcome these issues, we propose MMDG++, a multimodal domain-generalized FAS framework built upon the vision-language model CLIP. In MMDG++, we design the Uncertainty-Guided Cross-Adapter++ (U-Adapter++) to filter out unreliable regions within each modality, enabling more reliable multimodal interactions. Additionally, we introduce Rebalanced Modality Gradient Modulation (ReGrad) for adaptive gradient modulation to balance modality convergence. To further enhance generalization, propose Asymmetric Domain Prompts (ADPs) that leverage CLIP’s language priors to learn generalized decision boundaries across modalities. We also develop a novel multimodal FAS benchmark to evaluate generalizability under various deployment conditions. Extensive experiments across this benchmark show our method outperforms state-of-the-art FAS methods, demonstrating superior generalization capability.

1 July 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
RMRuohan Meng
Ruohan Meng
CYChenyu Yi
Chenyu Yi
YYYi Yu
Yi Yu
SYSiyuan Yang
Siyuan Yang
BSBingquan Shen
Bingquan Shen
AKAlex C. Kot
Alex C. Kot
Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are proposed to mislead the deep learning models and prevent data from unauthorized exploration by adding small perturbations to data. However, such perturbations (e.g., noise, texture, color change) predominantly impact low-level features, making them vulnerable to common countermeasures. In contrast, semantic images with intricate shapes have a wealth of high-level features, making them more resilient to countermeasures and potential for producing robust unlearnable examples. In this paper, we propose a Deep Hiding (DH) scheme that adaptively hides semantic images enriched with high-level features. We employ an Invertible Neural Network (INN) to invisibly integrate predefined images, inherently hiding them with deceptive perturbations. To enhance data unlearnability, we introduce a Latent Feature Concentration module, designed to work with the INN, regularizing the intra-class variance of these perturbations. To further boost the robustness of unlearnable examples, we design a Semantic Images Generation module that produces hidden semantic images. By utilizing similar semantic information, this module generates similar semantic images for samples within the same classes, thereby enlarging the inter-class distance and narrowing the intra-class distance. Extensive experiments on CIFAR-10, CIFAR-100, and an ImageNet subset, against 18 countermeasures, reveal that our proposed method exhibits outstanding robustness for unlearnable examples, demonstrating its efficacy in preventing unauthorized data exploitation.

28 November 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YYYi Yu
Yi Yu
YWYufei Wang
Yufei Wang
WYWenhan Yang
Wenhan Yang
LGLanqing Guo
Lanqing Guo
SLShijian Lu
Shijian Lu
AKAlex C. Kot
Alex C. Kot
Recent advancements in deep learning-based compression techniques have demonstrated remarkable performance surpassing traditional methods. Nevertheless, deep neural networks have been observed to be vulnerable to backdoor attacks, where an added pre-defined trigger pattern can induce the malicious behavior of the models. In this paper, we propose a novel approach to launch a backdoor attack with multiple triggers against learned image compression models. Drawing inspiration from the widely used discrete cosine transform (DCT) in existing compression codecs and standards, we propose a frequency-based trigger injection model that adds triggers in the DCT domain. In particular, we design several attack objectives that are adapted for a series of diverse scenarios, including: 1) attacking compression quality in terms of bit-rate and reconstruction quality; 2) attacking task-driven measures, such as face recognition and semantic segmentation in downstream applications. To facilitate more efficient training, we develop a dynamic loss function that dynamically balances the impact of different loss terms with fewer hyper-parameters, which also results in more effective optimization of the attack objectives with improved performance. Furthermore, we consider several advanced scenarios. We evaluate the resistance of the proposed backdoor attack to the defensive pre-processing methods and then propose a two-stage training schedule along with the design of robust frequency selection to further improve resistance. To strengthen both the cross-model and cross-domain transferability on attacking downstream CV tasks, we propose to shift the classification boundary in the attack loss during training. Extensive experiments also demonstrate that by employing our trained trigger injection models and making slight modifications to the encoder parameters of the compression model, our proposed attack can successfully inject multiple backdoors accompanied by their corresponding triggers into a single image compression model.

19 March 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YYYi Yu
Yi Yu
SXSong Xia
Song Xia
XLXun Lin
Xun Lin
CKChenqi Kong
Chenqi Kong
WYWenhan Yang
Wenhan Yang
AKAlex C. Kot
Alex C. Kot
Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive unseen models in black-box scenarios. Despite the widespread exploration of defense methods, including those on transferability, they show limitations: inefficient deployment, ineffective defense, and degraded performance on clean images. In this work, we introduce a novel training paradigm aimed at enhancing robustness against transferable adversarial examples (TAEs) in a more efficient and effective way.We propose a model that exhibits random guessing behavior when presented with clean data x as input, and generates accurate predictions when with triggered data x + τ . Importantly, the trigger τ remains constant for all data instances. We refer to these models as models with trigger activation. We are surprised to find that these models exhibit certain robustness against TAEs. Through the consideration of first-order gradients, we provide a theoretical analysis of this robustness. Moreover, through the joint optimization of the learnable trigger and the model, we achieve improved robustness to transferable attacks. Extensive experiments conducted across diverse datasets, evaluating a variety of attacking methods, underscore the effectiveness and superiority of our approach.

17 June 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YWYufei Wang
Yufei Wang
YYYi Yu
Yi Yu
WYWenhan Yang
Wenhan Yang
LGLanqing Guo
Lanqing Guo
LCLap-Pui Chau
Lap-Pui Chau
BWBihan Wen
Bihan Wen