Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works90 from public data
- Text Classification via Large Language Models296
Clue And Reasoning Prompting (CARP) adopts a progressive reasoning strategy tailored to addressing the complex linguistic phenomena involved in text classification, and achieves comparable performances to supervised models with 1,024 examples per class.
- DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation230
A systematic approach is proposed to discover the optimal policies for defending against different backdoor attacks by comprehensively evaluating 71 state-of-the-art data augmentation functions and envision this framework can be a good benchmark tool to advance future DNN backdoor studies.
- Triggerless Backdoor Attack for NLP Tasks with Clean Labels109
A new strategy to perform textual backdoor attack which does not require an external trigger and the poisoned samples are correctly labeled is proposed, which marks the first step towards developing triggerless attacking strategies in NLP.
- Byzantine-Resilient Decentralized Stochastic Gradient Descent88
Ubar is proposed, a novel algorithm to enhance decentralized learning with Byzantine Fault Tolerance that guarantees that each benign node in a decentralized system can train a correct model under very strong Byzantine attacks with an arbitrary number of faulty nodes.
- Privacy-preserving Collaborative Learning with Automatic Transformation Search67
This paper proposes to leverage data augmentation to defeat reconstruction attacks: by preprocessing sensitive images with carefully-selected transformation policies, it becomes infeasible for the adversary to extract any useful information from the corresponding gradients.
- Stealing Deep Reinforcement Learning Models for Fun and Profit56
This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only from its interaction with the environment.
- EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second53
The EvilEdit is proposed, a training-free and data-free backdoor attack against T2I diffusion models that can backdoor T2I diffusion models within one second with up to 100% success rate and preserves the functionality of the backdoored model using a protected whitelist.
- 49
- 48
- Towards efficient privacy-preserving face recognition in the cloud43
This paper proposes an affine transformation, which consists of permutation, diffusion and shift transformations, to protect the privacy of faces and proposes an optimization technique to increase the efficiency of encryption.
- 42
- Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models41
A novel watermark removal attack by combining imperceptible pattern embedding and spatial-level transformations, which can effectively and blindly destroy the memorization of watermarked models to the watermark samples.
- 40
- 36
- 35
- Processing secure, verifiable and efficient SQL over outsourced database34
This paper proposes a new cloud database model by introducing computation service providers (CSPs), which can accommodate the conventional DBaaS model; the CSPs undertake most of the postprocessing and reconstruction burden for database query.
- 33
- 30
- 30
- Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability27
This paper proposes a novel and severer backdoor attack, TransTroj, which enables the backdoors embedded in PTMs to efficiently transfer in the model supply chain and significantly outperforms SOTA task-agnostic backdoor attacks.
- Towards Byzantine-resilient Learning in Decentralized Systems26
Mozi provides a uniform Byzantine-resilient aggregation rule for benign nodes to select the useful parameter updates and filter out the malicious ones in each training iteration to achieve BFT in decentralized learning systems.
- BMIF: Privacy-preserving Blockchain-based Medical Image Fusion23
A privacy-preserving blockchain-based medical image fusion (BMIF) framework based on convolutional neural network and Inception network, and an efficient homomorphic encryption to realize the training of fusion model on encrypted medical data is proposed.
- 22
- Privacy-Aware Image Encryption Based on Logistic Map and Data Hiding22
This paper proposes a novel privacy-aware ROI image encryption (PRIE) scheme based on logistical mapping and data hiding that utilizes salient object detection to automatically, adaptively and accurately detect the privacy region of a given plain image.
- 21
- 21
- 20
- Ownership Verification of DNN Architectures via Hardware Cache Side Channels20
A novel watermarking scheme to achieve the ownership verification of DNN architectures by designing new algorithms based on Neural Architecture Search to generate watermarked architectures, which are unique enough to represent the ownership, while maintaining high model usability.
- 20
- Preventing Non-Intrusive Load Monitoring Privacy Invasion: A Precise Adversarial Attack Scheme for Networked Smart Meters19
A novel adversarial attack problem tailored specifically for NILM is formulated, providing a theoretical foundation for utilizing the Jacobian of the NILM model to generate imperceptible perturbations, which effectively misleads the signal prediction of NILM models to safeguard users’ appliance-level privacy.
- What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks19
A novel IP protection scheme for GANs where ownership verification can be done by checking outputs only, without choosing the inputs (i.e., box-free setting), that makes use of the unexploited potential of the discriminator to learn a hypersphere that captures the unique distribution learned by the paired generator.
- Topology-Aware Differential Privacy for Decentralized Image Classification19
The key insight of the TOP- DP solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability, which is the first DP optimization work from the perspective of network topologies.
- Benchmarking AlphaFold3-like Methods for Protein-Peptide Complex Prediction18
This study conducted predictions and comprehensive comparisons on two benchmark datasets of protein-short peptide complexes, and suggests that the main challenge for the performance decline comes from the accurate prediction of binding sites.
- 18
- 16
- Erase and Repair: An Efficient Box-Free Removal Attack on High-Capacity Deep Hiding16
A simple box-free removal attack on deep hiding that does not require any prior knowledge of the deep hiding schemes is proposed and a more powerful removal attack, efficient box- free removal attack (EBRA), which employs image inpainting techniques to remove secret images from container images is designed.
- ELAA: An efficient local adversarial attack using model interpreters16
A novel efficient local adversarial attack (ELAA) using model interpreters to generate severe local perturbations and improve the imperceptibly of the generated adversarial examples is proposed.
- Rethinking the Vulnerability of DNN Watermarking14
This paper investigates and introduces a novel watermark removal attack, called AdvNP, against all the existing four different types of DNN watermarking schemes via input preprocessing by injecting Adversarial Naturalness-aware Perturbations, and is the first work that generalizes allThe existing four watermarked schemes well without involving any model modification, which preserves the fidelity of the target model.
- 12
- SensIR: Towards privacy-sensitive image retrieval in the cloud12
A novel privacy-sensitive image retrieval scheme, named SensIR, to search for similar images from an outsourced image database and proposes a privacy region detection, PRDet, to prevent private regions of images from exposing and a systematic methodology to improve the accuracy of PCNN-based image retrieval when the privacy regions are large.
- EGM: An Efficient Generative Model for Unrestricted Adversarial Examples11
A novel decoupled two-step efficient generative model (EGM) is designed, which contains a conditional reference generator and a conditional adversarial transformer and can be also applied to existing attacks to improve their attack success rates, which is of independent interest.
- 11
- 11
- The Hidden Vulnerability of Watermarking for Deep Neural Networks.11
A novel watermark removal attack is designed, which can defeat state-of-the-art solutions without any prior knowledge of the adopted watermarking technique and training samples, and a novel preprocessing function is proposed, which embeds imperceptible patterns and performs spatial-level transformations over the input.
- 10
- 9
- 7
- 6
- Robust and privacy-preserving collaborative training: a comprehensive survey6
This survey seeks to provide a systematic and comprehensive evaluation of security and privacy studies in collaborative training, in contrast to prior surveys that only focus on one single collaborative learning system.
- AutoSched: An Adaptive Self-configured Framework for Scheduling Deep Learning Training Workloads6
AutoSched is a framework that can automatically, efficiently, and dynamically adjust the configuration parameters of DLT schedulers, and improves the performance of state-of-the-art schedulers by up to 46% with 132 × configuration tuning latency reduction.
- 6
- 6
- Text's Armor: Optimized Local Adversarial Perturbation Against Scene Text Editing Attacks6
This paper proposes to actively defeat text editing attacks by designing invisible "armors" for texts in the scene by turning the adversarial vulnerability of DNN-based STE into strength and design local perturbations specifically for texts using an optimized normalization strategy.
- Privacy-preserving Decentralized Deep Learning with Multiparty Homomorphic Encryption6
D-MHE is proposed, the first secure and efficient decentralized training framework with lossless precision that can reduce the communication complexity of general Secure Multiparty Computation tasks from quadratic to linear in the number of users, making it very suitable and scalable for large-scale decentralized learning systems.
- 6
- Differentially Private Decentralized Learning6
A novel DP-SGD algorithm for decentralized learning systems that leverages the unique network characteristics of decentralized systems to effectively reduce the noise scale and improve the model usability and a novel learning protocol for both synchronous and asynchronous decentralized systems.
- Efficient biometric identity-based encryption6
This paper proposes a provable-secure inner-product encryption (IPE) with short ciphertext and shows the IPE is indistinguishable against selective identity, adaptive chosen-plaintext attack (IND-sID-CPA), and constructs a distance-based encryption (DBE) leveraging the proposed IPE and proves that the DBE captures the same security with the underlying IPE.
- 5
- 5
- Image quality assessment based on multiscale fuzzy gradient similarity deviation5
A novel full-reference IQA (FR-IQA) scheme based on multiscale fuzzy gradient similarity deviation (MFGSD), where fuzzy inference system is introduced to reduce the negative impact of imperceptible distortions, and the standard deviation of fuzzygradient similarity is utilized to measure their quality distinction.
- 4
- 4
- 3
- Smaller Is Bigger: Rethinking the Embedding Rate of Deep Hiding3
A novel Local Deep Hiding (LDH) scheme that significantly increases the embedding rate by hiding large secret images into small local regions of cover images and exhibits superior robustness to common image distortions.
- 3
- 2
- Cognitive Tracing Data Trails: Auditing Data Provenance in Discriminative Language Models Using Accumulated Discrepancy Score2
A novel and efficient audit framework that helps users conduct cognitive analysis to determine if their textual data was used for data augmentation, and an analysis of how augmentation methods impact auditing performance.
- Towards Query-Efficient Black-Box Attacks: A Universal Dual Transferability-Based Framework2
This article proposes a novel black-box attack framework, constructed on a strategy of dual transferability (DT), to perturb the discriminative areas of clean examples within limited queries, and conducts extensive experiments to show that it can significantly improve the query efficiency of existing black- box attacks and attack success rates.
- 2
- Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning1
This study systematically examines the factors contributing to safety alignment degradation in benign fine-tuning scenarios and evaluates the reliability of state-of-the-art reward models (RMs), which are often used to guide alignment processes.
- 1
- 1
- 1
- Fingerprinting Image-to-Image Generative Adversarial Networks1
A novel finger-printing scheme for the Intellectual Property (IP) protection of image-to-image GANs based on a trusted third party and proves that these methods can satisfy different security requirements necessary for IP protection.
- Rethinking Adversarial Training with Neural Tangent Kernel1
An in-depth investigation of AT process and properties with NTK, such as NTK evolution, and the impact of data normalization on AT and the importance of unbiased estimators in batch normalization layers is disclosed.
- 1
- 1
- –
- –
- –
- ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs–
ShadeEdit is introduced, the first attack framework that leverages strengthened model editing to enable knowledge manipulation in FedIT scenarios and achieves an average 99.5% attack success rate over eight robust aggregation algorithms while preserving instruction-following accuracy, demonstrating its strong attack effectiveness and model-utility preservation.
- –
- –
- E-Sem3DGS: Monocular Human and Scene Reconstruction via Event-Aided Semantic 3DGS–
E-Sem3DGS is presented, a semantically augmented 3D Gaussian Splatting framework that leverages hybrid event-intensity streams to jointly reconstruct explicit 3D volumetric representations of human avatars and static scenes, and derives optical flow from events and uses it to supervise image-based optical flow between rendered frames, enforcing temporal coherence in high-motion regions and sharpening both humans and backgrounds.
- –
- –
- What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network–
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.