Siddharth Garg

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles

Extracting interesting scenarios from real-world data as well as generat...
03/12/2021 ∙ by Zahra Ghodsi, et al. ∙ 9 ∙ share

read it
DeepReDuce: ReLU Reduction for Fast Private Inference

The recent rise of privacy concerns has led researchers to devise method...
03/02/2021 ∙ by Nandan Kumar Jha, et al. ∙ 0 ∙ share

read it
On Graph Matching Using Generalized Seed Side-Information

In this paper, matching pairs of stocahstically generated graphs in the ...
02/11/2021 ∙ by Mahshad Shariatnasab, et al. ∙ 0 ∙ share

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...
11/08/2020 ∙ by Naman Patel, et al. ∙ 10 ∙ share

read it
Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection

This paper proposes a new defense against neural network backdooring att...
11/04/2020 ∙ by Hao Fu, et al. ∙ 0 ∙ share

read it
On Evaluating Neural Network Backdoor Defenses

Deep neural networks (DNNs) demonstrate superior performance in various ...
10/23/2020 ∙ by Akshaj Veldanda, et al. ∙ 0 ∙ share

read it
ASSURE: RTL Locking Against an Untrusted Foundry

Semiconductor design companies are integrating proprietary intellectual ...
10/11/2020 ∙ by Christian Pilato, et al. ∙ 0 ∙ share

read it
Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images

Unprecedented data collection and sharing have exacerbated privacy conce...
09/19/2020 ∙ by Kang Liu, et al. ∙ 6 ∙ share

read it
A Concentration of Measure Approach to Correlated Graph Matching

The graph matching problem emerges naturally in various applications suc...
08/30/2020 ∙ by Farhad Shirani, et al. ∙ 0 ∙ share

read it
Adversarially Robust Learning via Entropic Regularization

In this paper we propose a new family of algorithms for training adversa...
08/27/2020 ∙ by Gauri Jagatap, et al. ∙ 6 ∙ share

read it
CryptoNAS: Private Inference on a ReLU Budget

Machine learning as a service has given raise to privacy concerns surrou...
06/15/2020 ∙ by Zahra Ghodsi, et al. ∙ 0 ∙ share

read it
Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks

Deep learning (DL) offers potential improvements throughout the CAD tool...
04/26/2020 ∙ by Kang Liu, et al. ∙ 1 ∙ share

read it
NNoculation: Broad Spectrum and Targeted Treatment of Backdoored DNNs

This paper proposes a novel two-stage defense (NNoculation) against back...
02/19/2020 ∙ by Akshaj Kumar Veldanda, et al. ∙ 0 ∙ share

read it
On the Joint Typicality of Permutations of Sequences of Random Variables

Permutations of correlated sequences of random variables appear naturall...
01/20/2020 ∙ by Farhad Shirani, et al. ∙ 0 ∙ share

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 ...
06/25/2019 ∙ by Kang Liu, et al. ∙ 1 ∙ share

read it
Outsourcing Private Machine Learning via Lightweight Secure Arithmetic Computation

In several settings of practical interest, two parties seek to collabora...
12/04/2018 ∙ by Siddharth Garg, et al. ∙ 0 ∙ share

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 ...
11/05/2018 ∙ by Imran Hafeez Abbassi, et al. ∙ 0 ∙ share

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...
07/02/2018 ∙ by Jeff Zhang, et al. ∙ 0 ∙ share

read it
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks

Deep neural networks (DNNs) provide excellent performance across a wide ...
05/30/2018 ∙ by Kang Liu, et al. ∙ 0 ∙ share

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...
02/11/2018 ∙ by Jeff Zhang, et al. ∙ 0 ∙ share

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...
02/11/2018 ∙ by Zhang, et al. ∙ 0 ∙ share

read it
Optimal Checkpointing for Secure Intermittently-Powered IoT Devices

Energy harvesting is a promising solution to power Internet of Things (I...
11/04/2017 ∙ by Zahra Ghodsi, et al. ∙ 0 ∙ share

read it
Reverse Engineering Camouflaged Sequential Integrated Circuits Without Scan Access

Integrated circuit (IC) camouflaging is a promising technique to protect...
10/28/2017 ∙ by Mohamed El Massad, et al. ∙ 0 ∙ share

read it

Siddharth Garg

Featured Co-authors

Anima Anandkumar

Muhammad Shafique

Chinmay Hegde

Zhang

Elza Erkip

Kang Liu

Yuzhe Ma

Bei Yu

Faiq Khalid

Hao Fu

Ramesh Karri

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles

DeepReDuce: ReLU Reduction for Fast Private Inference

On Graph Matching Using Generalized Seed Side-Information

Bait and Switch: Online Training Data Poisoning of Autonomous Driving Systems

Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection

On Evaluating Neural Network Backdoor Defenses

ASSURE: RTL Locking Against an Untrusted Foundry

Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images

A Concentration of Measure Approach to Correlated Graph Matching

Adversarially Robust Learning via Entropic Regularization

CryptoNAS: Private Inference on a ReLU Budget

Bias Busters: Robustifying DL-based Lithographic Hotspot Detectors Against Backdooring Attacks

NNoculation: Broad Spectrum and Targeted Treatment of Backdoored DNNs

On the Joint Typicality of Permutations of Sequences of Random Variables

Are Adversarial Perturbations a Showstopper for ML-Based CAD? A Case Study on CNN-Based Lithographic Hotspot Detection

Outsourcing Private Machine Learning via Lightweight Secure Arithmetic Computation

TrojanZero: Switching Activity-Aware Design of Undetectable Hardware Trojans with Zero Power and Area Footprint

FATE: Fast and Accurate Timing Error Prediction Framework for Low Power DNN Accelerator Design

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks

ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Accelerators

Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Accelerator

Optimal Checkpointing for Secure Intermittently-Powered IoT Devices

Reverse Engineering Camouflaged Sequential Integrated Circuits Without Scan Access