Search Results for author: Damith C. Ranasinghe

Found 16 papers, 6 papers with code

Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Models

no code implementations31 Jan 2022 Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe

The ability to extract information from solely the output of a machine learning model to craft adversarial perturbations to black-box models is a practical threat against real-world systems, such as autonomous cars or machine learning models exposed as a service (MLaaS).

RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit

no code implementations10 Dec 2021 Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe

In our study, we first deep dive into recent state-of-the-art decision-based attacks in ICLR and SP to highlight the costly nature of discovering low distortion adversarial employing gradient estimation methods.

TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems

no code implementations19 Nov 2021 Bao Gia Doan, Minhui Xue, Shiqing Ma, Ehsan Abbasnejad, Damith C. Ranasinghe

Now, an adversary can arm themselves with a patch that is naturalistic, less malicious-looking, physically realizable, highly effective -- achieving high attack success rates, and universal.

Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables

no code implementations12 Oct 2021 Alireza Abedin, Hamid Rezatofighi, Damith C. Ranasinghe

Human activity recognition (HAR) is an important research field in ubiquitous computing where the acquisition of large-scale labeled sensor data is tedious, labor-intensive and time consuming.

Activity Recognition Representation Learning

Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense

no code implementations29 Sep 2021 Bao Gia Doan, Ehsan M Abbasnejad, Damith C. Ranasinghe

However, the learning approach for approximating the multi-modal Bayesian posterior leads to mode collapse with consequential sub-par robustness and under performance of an adversarially trained BNN.

Adversarial Defense

Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensors

no code implementations14 Jul 2020 Alireza Abedin, Mahsa Ehsanpour, Qinfeng Shi, Hamid Rezatofighi, Damith C. Ranasinghe

Wearables are fundamental to improving our understanding of human activities, especially for an increasing number of healthcare applications from rehabilitation to fine-grained gait analysis.

Activity Recognition

Super Low Resolution RF Powered Accelerometers for Alerting on Hospitalized Patient Bed Exits

1 code implementation19 Mar 2020 Michael Chesser, Asangi Jayatilaka, Renuka Visvanathan, Christophe Fumeaux, Alanson Sample, Damith C. Ranasinghe

The sensor design allows deriving ultra low resolution acceleration data from the rate of change of unique RFID tag identifiers in accordance with the movement of a patient's upper body.

Activity Recognition TAG

Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems

1 code implementation9 Aug 2019 Bao Gia Doan, Ehsan Abbasnejad, Damith C. Ranasinghe

Notably, in contrast to existing approaches, our approach removes the need for ground-truth labelled data or anomaly detection methods for Trojan detection or retraining a model or prior knowledge of an attack.

Cryptography and Security

SparseSense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks

no code implementations6 Jun 2019 Alireza Abedin, S. Hamid Rezatofighi, Qinfeng Shi, Damith C. Ranasinghe

Batteryless or so called passive wearables are providing new and innovative methods for human activity recognition (HAR), especially in healthcare applications for older people.

Activity Recognition

STRIP: A Defence Against Trojan Attacks on Deep Neural Networks

2 code implementations18 Feb 2019 Yansong Gao, Chang Xu, Derui Wang, Shiping Chen, Damith C. Ranasinghe, Surya Nepal

Since the trojan trigger is a secret guarded and exploited by the attacker, detecting such trojan inputs is a challenge, especially at run-time when models are in active operation.

Cryptography and Security

TrackerBots: Software in the Loop Study of Quad-Copter Robots for Locating Radio-tags in a 3D Space

1 code implementation1 Dec 2018 Hoa Van Nguyen, Hamid Rezatofighi, David Taggart, Bertram Ostendorf, Damith C. Ranasinghe

We investigate the problem of tracking and planning for a UAV in a task to locate multiple radio-tagged wildlife in a three-dimensional (3D) setting in the context of our TrackerBots research project.


Lightweight (Reverse) Fuzzy Extractor with Multiple Referenced PUF Responses

no code implementations19 May 2018 Yansong Gao, Yang Su, Lei Xu, Damith C. Ranasinghe

A Physical unclonable functions (PUF), alike a fingerprint, exploits manufacturing randomness to endow each physical item with a unique identifier.

Cryptography and Security

Real-Time Localization and Tracking of Multiple Radio-Tagged Animals with an Autonomous UAV

1 code implementation5 Dec 2017 Hoa Van Nguyen, Michael Chesser, Fei Chen, S. Hamid Rezatofighi, Damith C. Ranasinghe

Autonomous aerial robots provide new possibilities to study the habitats and behaviors of endangered species through the efficient gathering of location information at temporal and spatial granularities not possible with traditional manual survey methods.

Systems and Control Robotics

Modeling Attack Resilient Reconfigurable Latent Obfuscation Technique for PUF based Lightweight Authentication

no code implementations20 Jun 2017 Yansong Gao, Said F. Al-Sarawi, Derek Abbott, Ahmad-Reza Sadeghi, Damith C. Ranasinghe

Physical unclonable functions (PUFs), as hardware security primitives, exploit manufacturing randomness to extract hardware instance-specific secrets.

Cryptography and Security

Cannot find the paper you are looking for? You can Submit a new open access paper.