Search Results for author:
Found 26 papers, 6 papers with code
Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning
We demonstrate the effectiveness of both GI and LLL attacks in maliciously training models using the leaked data more accurately than a benign federated learning strategy.
Benchmarking Algorithms for Federated Domain Generalization
We then apply our methodology to evaluate 14 Federated DG methods, which include centralized DG methods adapted to the FL context, FL methods that handle client heterogeneity, and methods designed specifically for Federated DG.
The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning
We show that this resource overhead is caused by an incorrect perspective in all prior work that treats an attack on an aggregate update in the same way as an individual update with a larger batch size.
LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulation
When both FedAVG and secure aggregation are used, there is no current method that is able to attack multiple clients concurrently in a federated learning setting.
Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets
In this paper, we analyze four datasets from sensors deployed from manufacturing testbeds.
SmartAdapt: Multi-Branch Object Detection Framework for Videos on Mobiles
In this paper, we ask, and answer, the wide-ranging question across all MBODFs: How to expose the right set of execution branches and then how to schedule the optimal one at inference time?
Virtuoso: Video-based Intelligence for real-time tuning on SOCs
First, the system does not consider energy consumption of the models while making a decision on which model to run.
TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks
The attack uses the intuition that simply by changing the sign of the gradient updates that the optimizer is computing, for a set of malicious clients, a model can be diverted from the optima to increase the test error rate.
Resilience to Multiple Attacks via Adversarially Trained MIMO Ensembles
We show that ensemble methods can improve adversarial robustness to multiple attacks if the ensemble is \emph{adversarially diverse}, which is defined by two properties: 1) the sub-models are adversarially robust themselves and yet 2) adversarial attacks do not transfer easily between sub-models.
Automatic Forecasting via Meta-Learning
In this work, we develop techniques for fast automatic selection of the best forecasting model for a new unseen time-series dataset, without having to first train (or evaluate) all the models on the new time-series data to select the best one.
Federated Action Recognition on Heterogeneous Embedded Devices
Federated learning allows a large number of devices to jointly learn a model without sharing data.
Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests
While previous distribution shift detection approaches can identify if a shift has occurred, these approaches cannot localize which specific features have caused a distribution shift -- a critical step in diagnosing or fixing any underlying issue.
The Effect of Behavioral Probability Weighting in a Simultaneous Multi-Target Attacker-Defender Game
Each node has a certain value to the attacker and the defender, along with a probability of being successfully compromised, which is a function of the investments in that node by both players.
Anomaly Detection through Transfer Learning in Agriculture and Manufacturing IoT Systems
While there is a rich literature on anomaly detection in many IoT-based systems, there is no existing work that documents the use of ML models for anomaly detection in digital agriculture and in smart manufacturing systems.
Exploring Adversarial Examples via Invertible Neural Networks
We propose a new way of achieving such understanding through a recent development, namely, invertible neural models with Lipschitz continuous mapping functions from the input to the output.
Morshed: Guiding Behavioral Decision-Makers towards Better Security Investment in Interdependent Systems
We model the behavioral biases of human decision-making in securing interdependent systems and show that such behavioral decision-making leads to a suboptimal pattern of resource allocation compared to non-behavioral (rational) decision-making.
ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
In this paper we introduce ApproxDet, an adaptive video object detection framework for mobile devices to meet accuracy-latency requirements in the face of changing content and resource contention scenarios.
Can we Generalize and Distribute Private Representation Learning?
We study the problem of learning representations that are private yet informative, i. e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes.
BASCPS: How does behavioral decision making impact the security of cyber-physical systems?
We model the security investment decisions made by the defenders as a security game.
Cryptography and Security Computer Science and Game Theory
Distributed Inference with Sparse and Quantized Communication
We prove that our rule guarantees convergence to the true state exponentially fast almost surely despite sparse communication, and that it has the potential to significantly reduce information flow from uninformative agents to informative agents.
AppStreamer: Reducing Storage Requirements of Mobile Games through Predictive Streaming
AppStreamer can, therefore, keep only a small part of the files on the device, akin to a "cache", and download the remainder from a cloud storage server or a nearby edge server when it predicts that the app will need them in the near future.
SimVecs: Similarity-Based Vectors for Utterance Representation in Conversational AI Systems
Conversational AI systems are gaining a lot of attention recently in both industrial and scientific domains, providing a natural way of interaction between customers and adaptive intelligent systems.
HAWKEYE: Adversarial Example Detector for Deep Neural Networks
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images.
ApproxNet: Content and Contention-Aware Video Analytics System for Embedded Clients
None of the current approximation techniques for object classification DNNs can adapt to changing runtime conditions, e. g., changes in resource availability on the device, the content characteristics, or requirements from the user.
Misleading Metadata Detection on YouTube
YouTube is the leading social media platform for sharing videos.
ATHENA: Automated Tuning of Genomic Error Correction Algorithms using Language Models
The performance of most error-correction algorithms that operate on genomic sequencer reads is dependent on the proper choice of its configuration parameters, such as the value of k in k-mer based techniques.
