相关论文: Fusion: Efficient and Secure Inference Resilient t…

Underwater images suffer from severe degradations, including color distortions, reduced visibility, and loss of structural details due to wavelength-dependent attenuation and scattering. Existing enhancement methods primarily focus on…

Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of…

A multi-fidelity regression model is proposed for combining multiple datasets with different fidelities, particularly abundant low-fidelity data and scarce high-fidelity observations. The model builds upon recent multi-fidelity frameworks…

The decentralized Federated Learning (FL) setting avoids the role of a potentially unreliable or untrustworthy central host by utilizing groups of clients to collaboratively train a model via localized training and model/gradient sharing.…

Federated Learning (FL) facilitates collaborative model training among distributed clients while ensuring that raw data remains on local devices.Despite this advantage, FL systems are still exposed to risks from malicious or unreliable…

Diffusion models produce high quality images but inference is costly due to many denoising steps and heavy matrix operations. We present DiffPro, a post-training, hardware-faithful framework that works with the exact integer kernels used in…

Collaborative inference (CI) improves computational efficiency for edge devices by transmitting intermediate features to cloud models. However, this process inevitably exposes feature representations to model inversion attacks (MIAs),…

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by…

Cross-device Federated Learning is an increasingly popular machine learning setting to train a model by leveraging a large population of client devices with high privacy and security guarantees. However, communication efficiency remains a…

With the growth in digital transformation and Internet usage, the Social Engineering techniques such as Phishing have become a major concern for the users and the organizations. Phishing attacks involve deceptive techniques to trick users…

Modern user-facing latency-sensitive web services include numerous distributed, intercommunicating microservices that promise to simplify software development and operation. However, multiplexing of compute resources across microservices is…

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Users of social networks tend to post and share content with little restraint. Hence, rumors and fake news can quickly spread on a huge scale. This may pose a threat to the credibility of social media and can cause serious consequences in…

Federated Instruction Tuning (FIT) enables collaborative instruction tuning of large language models across multiple organizations (clients) in a cross-silo setting without requiring the sharing of private instructions. Recent findings on…

Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…

Federated Learning (FL) protects data privacy while providing a decentralized method for training models. However, because of the distributed schema, it is susceptible to adversarial clients that could alter results or sabotage model…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Federated learning is vulnerable to poisoning attacks in which malicious clients poison the global model via sending malicious model updates to the server. Existing defenses focus on preventing a small number of malicious clients from…

Submodular maximization is an optimization problem benefiting many machine learning applications, where we seek a small subset best representing an extremely large dataset. We focus on the federated setting where the data are locally owned…

In federated learning, multiple parties can cooperate to train the model without directly exchanging their own private data, but the gradient leakage problem still threatens the privacy security and model integrity. Although the existing…