Jiao Dai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiao Dai has a total of 64 co-authors. Here are the top co-authors by number of shared publications:
- Xiaomeng Fu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
13 shared publications - Jizhong Han
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
11 shared publications - Jin Liu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
10 shared publications - Jizhong Han
Chinese Academy of Sciences
10 shared publications - Xi Wang
Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China
10 shared publications - Cai Yu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5067-5076
Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5067-5076
Open AccessSemantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5058-5066
Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction of animation characters. Existing concept erasure methods fall short for animation character erasure: model modification methods struggle to identify suitable anchors for diverse, highly distinctive characters; prompt-based steering methods lack fine-grained control for precise intervention. These approaches often yield incomplete erasure and degraded image fidelity, hindering real-world deployment. In this paper, we propose a controllable method operating on the model's continuous textual representation to erase target characters during generation. We optimizes an anchor embedding via structural and detailed constraints to serve as a character surrogate, then replaces target-related embeddings with the anchor via a structure-aware adaptive strategy. Experiments show that our method achieves state-of-the-art erasure effectiveness and image fidelity preservation, while supporting controllable erasure degree, multi-target removal, and model transferability. Moreover, our optimized anchors are plug-and-play with current model modification baselines to improve their erasure performance.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5058-5066
Open AccessErase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction of animation characters. Existing concept erasure methods fall short for animation character erasure: model modification methods struggle to identify suitable anchors for diverse, highly distinctive characters; prompt-based steering methods lack fine-grained control for precise intervention. These approaches often yield incomplete erasure and degraded image fidelity, hindering real-world deployment. In this paper, we propose a controllable method operating on the model's continuous textual representation to erase target characters during generation. We optimizes an anchor embedding via structural and detailed constraints to serve as a character surrogate, then replaces target-related embeddings with the anchor via a structure-aware adaptive strategy. Experiments show that our method achieves state-of-the-art erasure effectiveness and image fidelity preservation, while supporting controllable erasure degree, multi-target removal, and model transferability. Moreover, our optimized anchors are plug-and-play with current model modification baselines to improve their erasure performance.
- 10 September 2026
- Published by Springer Nature
- p. 448-466
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
- 10 September 2026
- Published by Springer Nature
- p. 448-466
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
- 7 September 2026
- Published by Springer Nature
- p. 141-158
BAHSD: Bridging the Long-Tail Gap via Adaptive Distillation in Black-Box Sequential Recommendation
- 7 September 2026
- Published by Springer Nature
- p. 141-158
BAHSD: Bridging the Long-Tail Gap via Adaptive Distillation in Black-Box Sequential Recommendation
- 1 May 2026
- Published by Springer Nature
- p. 108-119
Causal Insights for Debiasing Recommender Systems: Future Directions and Challenges
- 1 May 2026
- Published by Springer Nature
- p. 108-119
Causal Insights for Debiasing Recommender Systems: Future Directions and Challenges
- Open Access
A Cognitive Distribution and Behavior-Consistent Framework for Black-Box Attacks on Recommender Systems
With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing black-box extraction attacks primarily rely on hard labels or pairwise learning, often ignoring the importance of ranking positions, which results in incomplete knowledge transfer. Moreover, adversarial sequences generated via pure gradient methods lack semantic consistency with real user behavior, making them easily detectable. To overcome these limitations, this paper proposes a dual-enhanced attack framework. First, drawing on primacy effects and position bias, we introduce a cognitive distribution-driven extraction mechanism that maps discrete rankings into continuous value distributions with position-aware decay, thereby advancing from order alignment to cognitive distribution alignment. Second, we design a behavior-aware noisy item generation strategy that jointly optimizes collaborative signals and gradient signals. This ensures both semantic coherence and statistical stealth while effectively promoting target item rankings. Extensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods in both attack success rate and evasion rate, validating the value of integrating cognitive modeling and behavioral consistency for secure recommender systems.
Open AccessA Cognitive Distribution and Behavior-Consistent Framework for Black-Box Attacks on Recommender Systems
With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing black-box extraction attacks primarily rely on hard labels or pairwise learning, often ignoring the importance of ranking positions, which results in incomplete knowledge transfer. Moreover, adversarial sequences generated via pure gradient methods lack semantic consistency with real user behavior, making them easily detectable. To overcome these limitations, this paper proposes a dual-enhanced attack framework. First, drawing on primacy effects and position bias, we introduce a cognitive distribution-driven extraction mechanism that maps discrete rankings into continuous value distributions with position-aware decay, thereby advancing from order alignment to cognitive distribution alignment. Second, we design a behavior-aware noisy item generation strategy that jointly optimizes collaborative signals and gradient signals. This ensures both semantic coherence and statistical stealth while effectively promoting target item rankings. Extensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods in both attack success rate and evasion rate, validating the value of integrating cognitive modeling and behavioral consistency for secure recommender systems.
- 24 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 3319-3334
FreeEdit: Mask-Free Reference-Based Image Editing With Multi-Modal Instruction
Introducing user-specified visual concepts in image editing is highly practical as these concepts convey the user's intent more precisely than text-based descriptions. We propose FreeEdit, a novel approach for achieving such reference-based image editing, which can accurately reproduce the visual concept from the reference image based on user-friendly language instructions. Our approach leverages the multi-modal instruction encoder to encode language instructions to guide the editing process. This implicit way of locating the editing area eliminates the need for manual editing masks. To enhance the reconstruction of reference details, we introduce the Decoupled Residual Refer-Attention (DRRA) module. This module is designed to integrate fine-grained reference features extracted by a detail extractor into the image editing process in a residual way without interfering with the original self-attention. Given that existing datasets are unsuitable for reference-based image editing tasks, particularly due to the difficulty in constructing image triplets that include a reference image, we curate a high-quality dataset, FreeBench, using a newly developed twice-repainting scheme. FreeBench comprises the images before and after editing, detailed editing instructions, as well as a reference image that maintains the identity of the edited object, encompassing tasks such as object addition, replacement, and deletion. By conducting phased training on FreeBench followed by quality tuning, FreeEdit achieves high-quality zero-shot editing through convenient language instructions. We conduct extensive experiments to evaluate the effectiveness of FreeEdit across multiple task types, demonstrating its superiority over existing methods.
- 24 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 3319-3334
FreeEdit: Mask-Free Reference-Based Image Editing With Multi-Modal Instruction
Introducing user-specified visual concepts in image editing is highly practical as these concepts convey the user's intent more precisely than text-based descriptions. We propose FreeEdit, a novel approach for achieving such reference-based image editing, which can accurately reproduce the visual concept from the reference image based on user-friendly language instructions. Our approach leverages the multi-modal instruction encoder to encode language instructions to guide the editing process. This implicit way of locating the editing area eliminates the need for manual editing masks. To enhance the reconstruction of reference details, we introduce the Decoupled Residual Refer-Attention (DRRA) module. This module is designed to integrate fine-grained reference features extracted by a detail extractor into the image editing process in a residual way without interfering with the original self-attention. Given that existing datasets are unsuitable for reference-based image editing tasks, particularly due to the difficulty in constructing image triplets that include a reference image, we curate a high-quality dataset, FreeBench, using a newly developed twice-repainting scheme. FreeBench comprises the images before and after editing, detailed editing instructions, as well as a reference image that maintains the identity of the edited object, encompassing tasks such as object addition, replacement, and deletion. By conducting phased training on FreeBench followed by quality tuning, FreeEdit achieves high-quality zero-shot editing through convenient language instructions. We conduct extensive experiments to evaluate the effectiveness of FreeEdit across multiple task types, demonstrating its superiority over existing methods.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 376-384
OMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models
The data-intensive nature of Diffusion models amplifies the risks of privacy infringements and copyright disputes, particularly when training on extensive unauthorized data scraped from the Internet. Membership Inference Attacks (MIA) aim to determine whether a data sample has been utilized by the target model during training, thereby serving as a pivotal tool for privacy preservation. Current MIA employs the prediction loss to distinguish between training member samples and non-members. These methods assume that, compared to non-members, members, having been encountered by the model during training result in a smaller prediction loss. However, this assumption proves ineffective in diffusion models due to the random noise sampled during the training process. Rather than estimating the loss, our approach examines this random noise and reformulate the MIA as a noise search problem, assuming that members are more feasible to find the noise used in the training process. We formulate this noise search process as an optimization problem and employ the fixed-point iteration to solve it. We analyze current MIA methods through the lens of the noise search framework and reveal that they rely on the first residual as the discriminative metric to differentiate members and non-members. Inspired by this observation, we introduce OMS, which augments existing MIA methods by iterating One More fixed-point Step to include a further residual, i.e., the second residual. We integrate our method into various MIA methods across different diffusion models. The experimental results validate the efficacy of our proposed approach.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 376-384
Open AccessOMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models
The data-intensive nature of Diffusion models amplifies the risks of privacy infringements and copyright disputes, particularly when training on extensive unauthorized data scraped from the Internet. Membership Inference Attacks (MIA) aim to determine whether a data sample has been utilized by the target model during training, thereby serving as a pivotal tool for privacy preservation. Current MIA employs the prediction loss to distinguish between training member samples and non-members. These methods assume that, compared to non-members, members, having been encountered by the model during training result in a smaller prediction loss. However, this assumption proves ineffective in diffusion models due to the random noise sampled during the training process. Rather than estimating the loss, our approach examines this random noise and reformulate the MIA as a noise search problem, assuming that members are more feasible to find the noise used in the training process. We formulate this noise search process as an optimization problem and employ the fixed-point iteration to solve it. We analyze current MIA methods through the lens of the noise search framework and reveal that they rely on the first residual as the discriminative metric to differentiate members and non-members. Inspired by this observation, we introduce OMS, which augments existing MIA methods by iterating One More fixed-point Step to include a further residual, i.e., the second residual. We integrate our method into various MIA methods across different diffusion models. The experimental results validate the efficacy of our proposed approach.
- 24 June 2025
- Published by Springer Nature
- p. 31-46
EPRVR: Efficient Partially Relevant Video Retrieval with Disentangled Video Representation Learning
- 24 June 2025
- Published by Springer Nature
- p. 31-46
EPRVR: Efficient Partially Relevant Video Retrieval with Disentangled Video Representation Learning
- Open Access
- 17 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 12-23
Modality-Agnostic Deepfakes Detection
- 17 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 12-23
Open AccessModality-Agnostic Deepfakes Detection