Search Results for author:
Found 14 papers, 8 papers with code
ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction
Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces.
Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture
Vector Symbolic Architecture (VSA) is emerging in machine learning due to its efficiency, but they are hindered by issues of hyperdimensionality and accuracy.
LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models
Our results show that LightPure can outperform existing methods by up to 10x in terms of latency while achieving higher accuracy and robustness for various attack scenarios.
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
To achieve both goals, a mainstream class of LLM unlearning methods introduces an optimization framework with a combination of two objectives - maximizing the prediction loss on the forget documents while minimizing that on the retain documents, which suffers from two challenges, degenerated output and catastrophic forgetting.
Efficient Multitask Dense Predictor via Binarization
Moreover, we introduce a knowledge distillation mechanism to correct the direction of information flow in backward propagation.
A Survey on Large Language Model-Based Game Agents
The development of game agents holds a critical role in advancing towards Artificial General Intelligence.
Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Study
(3) However, algorithms such as FedDyn and SCAFFOLD are more prone to catastrophic failures without the support of additional techniques such as gradient clipping.
Urban Scene Diffusion through Semantic Occupancy Map
Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation.
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications.
Enhancing Post-training Quantization Calibration through Contrastive Learning
We aim to calibrate the quantized activations by maximizing the mutual information between the pre- and post-quantized activations.
Graphene: Infrastructure Security Posture Analysis with AI-generated Attack Graphs
In this paper, we propose Graphene, an advanced system designed to provide a detailed analysis of the security posture of computing infrastructures.
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
This is because the art necessitates modifications to the diffusion training and sampling procedures.
Riemannian Multinomial Logistics Regression for SPD Neural Networks
Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks.
Flame: Simplifying Topology Extension in Federated Learning
We present Flame, a new system that provides flexibility of the topology configuration of distributed FL applications around the specifics of a particular deployment context, and is easily extensible to support new FL architectures.
