NDLI: Resilient linear classification: an approach to deal with attacks on training data

Please wait, while we are loading the content...

Sampling-based control synthesis for multi-robot systems under global temporal specifications

Battery state-of-health estimation for mobile devices

A physiology-aware communication architecture for distributed emergency medical CPS

Constructing compact causal mathematical models for complex dynamics

VirtualDrone: virtual sensing, actuation, and communication for attack-resilient unmanned aerial systems

Privacy-enhanced architecture for occupancy-based HVAC Control

A merging protocol for self-driving vehicles

Data-driven distributionally robust vehicle balancing using dynamic region partitions

Formal synthesis of distributed optimal traffic control policies

SunShade: enabling software-defined solar-powered systems

Cybermanufacturing in the shared economy

Analyzing neighborhoods of falsifying traces in cyber-physical systems

Resilient linear classification: an approach to deal with attacks on training data

A submodular optimization approach to controlled islanding under cascading failure

GreenDrive: a smartphone-based intelligent speed adaptation system with real-time traffic signal prediction

Markov decision process routing games

Multi-objective optimal control with safety as a priority

Distributed placement of power generation resources in uncertain environments

Diagnostics and prognostics using temporal causal models for cyber physical energy systems

Abstraction based reachability analysis for finite branching stochastic hybrid systems

Resilient sensor placement for fault localization in water distribution networks

Application and system-level software fault tolerance through full system restarts

DRONA: a framework for safe distributed mobile robotics

QuActive: a quality of activities monitoring and notification system

Enhancing tolerance to unexpected jumps in GR(1) games

Towards a framework for comprehensive and systematic reliability evaluation of building management systems

A Gaussian process regression approach to model aircraft engine fuel flow rate

Hardware module-based message authentication in intra-vehicle networks

Provably-correct coordination of large collections of agents with counting temporal logic constraints

Personalization without user interruption: boosting activity recognition in new subjects using unlabeled data

Transactive energy demo with RIAPS platform

Platform for security-aware design of human-on-the-loop cyber-physical systems

Resilient linear classification: an approach to deal with attacks on training data

Content Provider	ACM Digital Library
Author	Weimer, James Lee, Insup Park, Sangdon
Abstract	Data-driven techniques are used in cyber-physical systems (CPS) for controlling autonomous vehicles, handling demand responses for energy management, and modeling human physiology for medical devices. These data-driven techniques extract models from training data, where their performance is often analyzed with respect to random errors in the training data. However, if the training data is maliciously altered by attackers, the effect of these attacks on the learning algorithms underpinning data-driven CPS have yet to be considered. In this paper, we analyze the resilience of classification algorithms to training data attacks. Specifically, a generic metric is proposed that is tailored to measure resilience of classification algorithms with respect to worst-case tampering of the training data. Using the metric, we show that traditional linear classification algorithms are resilient under restricted conditions. To overcome these limitations, we propose a linear classification algorithm with a majority constraint and prove that it is strictly more resilient than the traditional algorithms. Evaluations on both synthetic data and a real-world retrospective arrhythmia medical case-study show that the traditional algorithms are vulnerable to tampered training data, whereas the proposed algorithm is more resilient (as measured by worst-case tampering).
Starting Page	155
Ending Page	164
Page Count	10
File Format	PDF
ISBN	9781450349659
DOI	10.1145/3055004.3055006
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2017-04-18
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Linear classification Cyber-physical systems Training data attacks
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Resilient Linear Classification: An Approach to Deal with Attacks on Training Data

On Addressing the Security and Stability Issues Due to False Data Injection Attacks in DC Microgrids—An Adaptive Observer Approach

Classification of and resilience to cyber-attacks on cyber-physical systems

A Resilient Control Approach to Secure Cyber Physical Systems (CPS) with an Application on Connected Vehicles

Inclusion of game-theoretic formulations for resilient condition assessment monitoring

A resilient condition assessment monitoring system

Anomaly-Based Detection and Classification of Attacks in Cyber-Physical Systems

Integrity attacks on cyber-physical systems

An Event-Triggered Fault Detection Approach in Cyber-Physical Systems with Sensor Nonlinearities and Deception Attacks

Resilient linear classification: an approach to deal with attacks on training data

Similar Documents

Resilient Linear Classification: An Approach to Deal with Attacks on Training Data

On Addressing the Security and Stability Issues Due to False Data Injection Attacks in DC Microgrids—An Adaptive Observer Approach

Classification of and resilience to cyber-attacks on cyber-physical systems

A Resilient Control Approach to Secure Cyber Physical Systems (CPS) with an Application on Connected Vehicles

Inclusion of game-theoretic formulations for resilient condition assessment monitoring

A resilient condition assessment monitoring system

Anomaly-Based Detection and Classification of Attacks in Cyber-Physical Systems

Integrity attacks on cyber-physical systems

An Event-Triggered Fault Detection Approach in Cyber-Physical Systems with Sensor Nonlinearities and Deception Attacks

Resilient linear classification: an approach to deal with attacks on training data