
-
Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles
Extracting interesting scenarios from real-world data as well as generat...
read it
-
DeepReDuce: ReLU Reduction for Fast Private Inference
The recent rise of privacy concerns has led researchers to devise method...
read it
-
On Graph Matching Using Generalized Seed Side-Information
In this paper, matching pairs of stocahstically generated graphs in the ...
read it
-
Bait and Switch: Online Training Data Poisoning of Autonomous Driving Systems
We show that by controlling parts of a physical environment in which a p...
read it
-
Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection
This paper proposes a new defense against neural network backdooring att...
read it
-
On Evaluating Neural Network Backdoor Defenses
Deep neural networks (DNNs) demonstrate superior performance in various ...
read it
-
ASSURE: RTL Locking Against an Untrusted Foundry
Semiconductor design companies are integrating proprietary intellectual ...
read it
-
Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images
Unprecedented data collection and sharing have exacerbated privacy conce...
read it
-
A Concentration of Measure Approach to Correlated Graph Matching
The graph matching problem emerges naturally in various applications suc...
read it
-
Adversarially Robust Learning via Entropic Regularization
In this paper we propose a new family of algorithms for training adversa...
read it
-
CryptoNAS: Private Inference on a ReLU Budget
Machine learning as a service has given raise to privacy concerns surrou...
read it
-
Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks
Deep learning (DL) offers potential improvements throughout the CAD tool...
read it
-
NNoculation: Broad Spectrum and Targeted Treatment of Backdoored DNNs
This paper proposes a novel two-stage defense (NNoculation) against back...
read it
-
On the Joint Typicality of Permutations of Sequences of Random Variables
Permutations of correlated sequences of random variables appear naturall...
read it
-
Are Adversarial Perturbations a Showstopper for ML-Based CAD? A Case Study on CNN-Based Lithographic Hotspot Detection
There is substantial interest in the use of machine learning (ML) based ...
read it
-
Outsourcing Private Machine Learning via Lightweight Secure Arithmetic Computation
In several settings of practical interest, two parties seek to collabora...
read it
-
TrojanZero: Switching Activity-Aware Design of Undetectable Hardware Trojans with Zero Power and Area Footprint
Conventional Hardware Trojan (HT) detection techniques are based on the ...
read it
-
FATE: Fast and Accurate Timing Error Prediction Framework for Low Power DNN Accelerator Design
Deep neural networks (DNN) are increasingly being accelerated on applica...
read it
-
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Deep neural networks (DNNs) provide excellent performance across a wide ...
read it
-
ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Accelerators
Hardware accelerators are being increasingly deployed to boost the perfo...
read it
-
Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Accelerator
Due to their growing popularity and computational cost, deep neural netw...
read it
-
Optimal Checkpointing for Secure Intermittently-Powered IoT Devices
Energy harvesting is a promising solution to power Internet of Things (I...
read it
-
Reverse Engineering Camouflaged Sequential Integrated Circuits Without Scan Access
Integrated circuit (IC) camouflaging is a promising technique to protect...
read it