157 citations · 929 across the 89 of their papers we have counts for
27 papers · 1 filter
Test-Time Adaptation for Unsupervised Combinatorial Optimization
Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh
Unsupervised neural combinatorial optimization (NCO) enables learning powerful solvers without access to ground-truth solutions. Existing approaches fall into two disjoint paradigm…
Learning for Dynamic Combinatorial Optimization without Training Data
Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh
We introduce DyCO-GNN, a novel unsupervised learning framework for Dynamic Combinatorial Optimization that requires no training data beyond the problem instance itself. DyCO-GNN le…
DROP: Poison Dilution via Knowledge Distillation for Federated Learning
Georgios Syros, Anshuman Suri, Farinaz Koushanfar +2
Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense m…
Trojan Cleansing with Neural Collapse
Xihe Gu, Greg Fields, Yaman Jandali +2
Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific output on any input which inclu…
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
Mingjia Huo, Sai Ashish Somayajula, Youwei Liang +3
Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts. Wa…
LayerCollapse: Adaptive compression of neural networks
Soheil Zibakhsh Shabgahi, Mohammad Sohail Shariff, Farinaz Koushanfar
Handling the ever-increasing scale of contemporary deep learning and transformer-based models poses a significant challenge. Overparameterized Transformer networks outperform prior…
LiveTune: Dynamic Parameter Tuning for Feedback-Driven Optimization
Soheil Zibakhsh Shabgahi, Nojan Sheybani, Aiden Tabrizi +1
Feedback-driven optimization, such as traditional machine learning training, is a static process that lacks real-time adaptability of hyperparameters. Tuning solutions for optimiza…
SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection
Nasimeh Heydaribeni, Ruisi Zhang, Tara Javidi +2
In this work, we introduce SureFED, a novel framework for byzantine robust federated learning. Unlike many existing defense methods that rely on statistically robust quantities, ma…
PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications
Diego Garcia-soto, Huili Chen, Farinaz Koushanfar
Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks. Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and i…
zPROBE: Zero Peek Robustness Checks for Federated Learning
Zahra Ghodsi, Mojan Javaheripi, Nojan Sheybani +3
Privacy-preserving federated learning allows multiple users to jointly train a model with coordination of a central server. The server only learns the final aggregation result, thu…
Adversarial Scratches: Deployable Attacks to CNN Classifiers
Loris Giulivi, Malhar Jere, Loris Rossi +4
A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model's input which le…
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models
Mojan Javaheripi, Gustavo H. de Rosa, Subhabrata Mukherjee +6
The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off bet…
Machine Learning-Assisted E-jet Printing of Organic Flexible Biosensors
Mehran Abbasi Shirsavar, Mehrnoosh Taghavimehr, Lionel J. Ouedraogo +4
Electrohydrodynamic-jet (e-jet) printing technique enables the high-resolution printing of complex soft electronic devices. As such, it has an unmatched potential for becoming the…
Trojan Signatures in DNN Weights
Greg Fields, Mohammad Samragh, Mojan Javaheripi +2
Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model…
Unsupervised Information Obfuscation for Split Inference of Neural Networks
Mohammad Samragh, Hossein Hosseini, Aleksei Triastcyn +3
Splitting network computations between the edge device and a server enables low edge-compute inference of neural networks but might expose sensitive information about the test quer…
CLEANN: Accelerated Trojan Shield for Embedded Neural Networks
Mojan Javaheripi, Mohammad Samragh, Gregory Fields +2
We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications. A Trojan attack works by injecting…
GeneCAI: Genetic Evolution for Acquiring Compact AI
Mojan Javaheripi, Mohammad Samragh, Tara Javidi +1
In the contemporary big data realm, Deep Neural Networks (DNNs) are evolving towards more complex architectures to achieve higher inference accuracy. Model compression techniques c…
Principal Component Properties of Adversarial Samples
Malhar Jere, Sandro Herbig, Christine Lind +1
Deep Neural Networks for image classification have been found to be vulnerable to adversarial samples, which consist of sub-perceptual noise added to a benign image that can easily…
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent +56
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a cen…
ASCAI: Adaptive Sampling for acquiring Compact AI
Mojan Javaheripi, Mohammad Samragh, Tara Javidi +1
This paper introduces ASCAI, a novel adaptive sampling methodology that can learn how to effectively compress Deep Neural Networks (DNNs) for accelerated inference on resource-cons…
Universal Adversarial Perturbations for Speech Recognition Systems
Paarth Neekhara, Shehzeen Hussain, Prakhar Pandey +3
In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems.…
SWNet: Small-World Neural Networks and Rapid Convergence
Mojan Javaheripi, Bita Darvish Rouhani, Farinaz Koushanfar
Training large and highly accurate deep learning (DL) models is computationally costly. This cost is in great part due to the excessive number of trained parameters, which are well…
Peer-to-peer Federated Learning on Graphs
Anusha Lalitha, Osman Cihan Kilinc, Tara Javidi +1
We consider the problem of training a machine learning model over a network of nodes in a fully decentralized framework. The nodes take a Bayesian-like approach via the introductio…
CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNs
Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar
This paper proposes CodeX, an end-to-end framework that facilitates encoding, bitwidth customization, fine-tuning, and implementation of neural networks on FPGA platforms. CodeX in…