Search Results for author:
Found 29 papers, 5 papers with code
Identity-Focused Inference and Extraction Attacks on Diffusion Models
The increasing reliance on diffusion models for generating synthetic images has amplified concerns about the unauthorized use of personal data, particularly facial images, in model training.
PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models
Yet, direct application of PTQ to diffusion models can degrade synthesis quality due to accumulated quantization noise across multiple denoising steps, particularly in conditional tasks like text-to-audio synthesis.
Augmented Efficiency: Reducing Memory Footprint and Accelerating Inference for 3D Semantic Segmentation through Hybrid Vision
We perform rigorous evaluations with the DeepViewAgg model on the complete point cloud as our baseline by measuring the Intersection over Union (IoU) accuracy, inference time latency, and memory consumption.
FedDM: Enhancing Communication Efficiency and Handling Data Heterogeneity in Federated Diffusion Models
We propose a suite of training algorithms that leverage the U-Net architecture as the backbone for our diffusion models.
Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing
To bridge this gap, we propose relevance paraphrasing, a simple strategy that can be used to measure the robustness of LLMs as summarizers.
Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning
Sample efficiency remains a key challenge in multi-agent reinforcement learning (MARL).
Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
In this paper, we establish a bridge between identifying detrimental training samples via influence functions and outlier gradient detection.
Robust Explainable Recommendation
In this work, we present a general framework for feature-aware explainable recommenders that can withstand external attacks and provide robust and generalized explanations.
Stability of Explainable Recommendation
Experimental results verify our hypothesis that the ability to explain recommendations does decrease along with increasing noise levels and particularly adversarial noise does contribute to a much stronger decrease.
Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias
We characterize and study zero-shot abstractive summarization in Large Language Models (LLMs) by measuring position bias, which we propose as a general formulation of the more restrictive lead bias phenomenon studied previously in the literature.
Multi-agent Reinforcement Learning: A Comprehensive Survey
Multi-agent systems (MAS) are widely prevalent and crucially important in numerous real-world applications, where multiple agents must make decisions to achieve their objectives in a shared environment.
Fairness Uncertainty Quantification: How certain are you that the model is fair?
We provide online multiplier bootstrap method to estimate the asymptotic covariance to construct online CI.
Decentralized Multi-agent Filtering
This paper addresses the considerations that comes along with adopting decentralized communication for multi-agent localization applications in discrete state spaces.
Federated Learning Hyper-Parameter Tuning from a System Perspective
In this paper, we propose FedTune, an automatic FL hyper-parameter tuning algorithm tailored to applications' diverse system requirements in FL training.
Robust Fair Clustering: A Novel Fairness Attack and Defense Framework
Experimentally, we observe that CFC is highly robust to the proposed attack and is thus a truly robust fair clustering alternative.
On the Robustness of Deep Clustering Models: Adversarial Attacks and Defenses
Clustering models constitute a class of unsupervised machine learning methods which are used in a number of application pipelines, and play a vital role in modern data science.
Fairness Degrading Adversarial Attacks Against Clustering Algorithms
As a first step, we propose a fairness degrading attack algorithm for k-median clustering that operates under a whitebox threat model -- where the clustering algorithm, fairness notion, and the input dataset are known to the adversary.
FedTune: Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
Federated learning (FL) hyper-parameters significantly affect the training overheads in terms of computation time, transmission time, computation load, and transmission load.
Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
Federated Learning (FL) is a distributed model training paradigm that preserves clients' data privacy.
Fair Clustering Using Antidote Data
Extensive experiments on different clustering algorithms and fairness notions show that our algorithms can achieve desired levels of fairness on many real-world datasets with a very small percentage of antidote data added.
Escaping Saddle-Point Faster under Interpolation-like Conditions
We next analyze Stochastic Cubic-Regularized Newton (SCRN) algorithm under interpolation-like conditions, and show that the oracle complexity to reach an $\epsilon$-local-minimizer under interpolation-like conditions, is $O(1/\epsilon^{2. 5})$.
Escaping Saddle-Points Faster under Interpolation-like Conditions
We next analyze Stochastic Cubic-Regularized Newton (SCRN) algorithm under interpolation-like conditions, and show that the oracle complexity to reach an $\epsilon$-local-minimizer under interpolation-like conditions, is $\tilde{\mathcal{O}}(1/\epsilon^{2. 5})$.
Towards Learning-automation IoT Attack Detection through Reinforcement Learning
These low-rate attacks are challenging to detect and can persist in the networks.
Fair Algorithms for Hierarchical Agglomerative Clustering
Hierarchical Agglomerative Clustering (HAC) algorithms are extensively utilized in modern data science, and seek to partition the dataset into clusters while generating a hierarchical relationship between the data samples.
Online and Bandit Algorithms for Nonstationary Stochastic Saddle-Point Optimization
We establish sub-linear regret bounds on the proposed notions of regret in both the online and bandit setting.
Suspicion-Free Adversarial Attacks on Clustering Algorithms
To the best of our knowledge, this is the first work that generates spill-over adversarial samples without the knowledge of the true metric ensuring that the perturbed sample is not an outlier, and theoretically proves the above.
Multi-Point Bandit Algorithms for Nonstationary Online Nonconvex Optimization
In this paper, motivated by online reinforcement learning problems, we propose and analyze bandit algorithms for both general and structured nonconvex problems with nonstationary (or dynamic) regret as the performance measure, in both stochastic and non-stochastic settings.
Strong Black-box Adversarial Attacks on Unsupervised Machine Learning Models
We first provide a strong (iterative) black-box adversarial attack that can craft adversarial samples which will be incorrectly clustered irrespective of the choice of clustering algorithm.
When to Reset Your Keys: Optimal Timing of Security Updates via Learning
As these attacks are often designed to disable a system (or a critical resource, e. g., a user account) repeatedly, it is crucial for the defender to keep updating its security measures to strike a balance between the risk of being compromised and the cost of security updates.
