Anmol Sheth

I am a Senior Research Scientist at (Amazon) where I work on building data driven products at the intersection of Amazon-scale retail data and Internet-scale advertising data and systems. 

Prior to A9, I worked at Intel Labs Seattle and Technicolor Research Lab Palo Alto. I graduated with a Ph.D. in Computer Science from University of Colorado, Boulder and completed my undergrad from P.I.C.T Pune, India.

Past Research Projects:

Enabling transparency in online targeted advertising: Developing a measurement platform that enables users to reason about how their browsing habits impacts the ads targeted at them. See our HotNets 2013 paper for more details.

Auditable data mining platform: Building data mining platforms that simplify and reduce the cost of data audits.

Cloud Assisted Interactive Mobile Perception: Developing systems support to enable cloud-assisted interactive perception like real time face, gesture and object recognition on mobile devices. 

Motivating an App Store for the Home (MASH):
Developing technical mechanisms to provide end-users transparency and control over the collection and use of data by rich sensing applications in the home.

Trustworthy Wireless:
Mobile and wireless devices that preserve user privacy.

WiLDNet: Low cost network connectivity solution to rural and remote areas using Wi-Fi based long distance networks.

Software Release:

802.11n Channel Measurement Tool: We have released the Linux drivers and firmware for the Intel 5300 MIMO radios to perform channel measurements. You can download the source code and instructions from here.

Professional Activities:

PC Member: IMC 2014,  CoNext 2013, Mobicom 2011, MobiSys 2011, MobiHoc 2010, WiMesh 2010

Co-chair: ACM HomeSys 2012,  WiNMee 2009


List of all papers is available here.

  • "

    Unraveling the Relationship Between Ad-Injecting Browser Extensions and Malvertising


    Xinyu Xing, Wei Meng, Udi Weinsberg, Anmol Sheth, Byoungyoung Lee, Wenke Lee and Roberto Perdisci
    WWW 2015
  • "

    Your Online Interests – Pwned! A Pollution Attack Against Targeted Advertising 


    Wei Meng, Xinyu Xing, Anmol Sheth, Udi Weinsberg, Wenke Lee
    ACM CCS 2014
        • "

          AdReveal: Improving Transparency Into Online Targeted Advertising


          Bin Liu, Anmol Sheth, Udi Weinsberg, Jaideep Chandrashekar, Ramesh Govindan
          HotNets 2013
        • "

          Predicting Audience Responses to Movie Content from Electro-Dermal Activity Signals


          Fernando Silveira, Brian Eriksson, Anmol Sheth and Adam Sheppard
          ACM UbiComp 2013
              • "Towards User Identification in the Home Using Appliance Usage Patterns


                Daniel Garnier-Moiroux, Fernando Silveira and Anmol Sheth
                HomeSys 2013
                • "

                  Snooze: Energy Management in 802.11n"

                  Ki-Young Jang, Shuai Hao, Anmol Sheth and Ramesh Govindan
                  CoNext 2011
                • "

                  YouProve: Authenticity and Fidelity in Mobile Sensing"

                  Peter Gilbert, Jaeyeon Jung, Kyugmin Lee, Henry Qin, Daniel Sharkey, Anmol Sheth, and Landon P. Cox
                  SenSys 2011
                • "

                  Uplink Traffic Control in Home 802.11 Wireless Networks"

                  Yanlin Li, Konstantina Papagiannaki, and Anmol Sheth
                  ACM SIGOMM Workshop HomeNets 2011
                • "Odessa: Enabling Interactive Perception Applications on Mobile Devices" [pdf]
                  Moo-Ryong Ra, Anmol Sheth, Lily Mummert, Padmanabhan Pillai,
                  David Wetherall and Ramesh Govindan
                  MobiSys 2011

                • "Sensor Tricorder: What does that sensor know about me?" [pdf]
                  Gabriel Maganis, Jaeyeon Jung, Tadayoshi Kohno, Anmol Sheth and David Wetherall
                  HotMobile 2011
                • "Demystifying 802.11n Power Consumption" [pdf]
                  Daniel Halperin, Ben Greenstein, Anmol Sheth and David Wetherall
                  HotPower 2010
                  Provides detailed power measurements for a commercial 802.11n NIC and reevaluates commonnly used techniques for power-efficient Wi-Fi communication.
                • "TaintDroid: An Information-Flow Tracking System for Realtime Privacy Monitoring on Smartphones" [web page] 
                  William Enck, Peter Gilbert, Byung-gon Chun, Landon P. Cox, Jaeyeon Jung, Patrick McDaniel, and Anmol Sheth
                  OSDI 2010
                • "Pushing the Envelope of Indoor Wireless Spatial Reuse using Directional Access Points and Clients" [pdf]
                  Xi Liu, Anmol Sheth, Michael Kaminsky, Konstantina Papagiannaki, Srinivasan Seshan, Peter Steenkiste
                  Mobicom 2010
                  Explores the design space of antenna placement and MAC protocols for indoor directional antenna systems.
                • "Investigation into the Doppler Component of the IEEE 802.11n Channel Model" [pdf]
                  Eldad Perahia, Anmol Sheth, Thomas Kenny, Robert Stacey, Daniel Halperin
                  Globecom 2010
                  Highlights the performance mismatch of MIMO beamforming between the 802.11n channel model and real channel measurements from commodity NICs.
                • "Predictable 802.11 Packet Delivery from Wireless Channel Measurements" [pdf]
                  Dan Halperin, Wenjun Hu, Anmol Sheth, David Wetherall
                  SIGCOMM 2010
                  Uses channel measurements from commodity 802.11 NICs to accurately predict packet delivery for SISO and MIMO rates
                • "Ensemble: Cooperative Proximity-based Authentication" [pdf]
                  Andre Kalamandeen, Adin Scannell, Eyal de Lara, Anmol Sheth, Anthony LaMarca
                  MobiSys 2010
                  Uses a collection of trusted personal devices to provide proximity-based authentication.
                • "802.11 With Multiple Antennas for Dummies" [pdf]
                  Dan Halperin, Wenjun Hu, Anmol Sheth, David Wetherall
                  CCR 2010
                  Short tutorial on 802.11n based MIMO targeted for networking researchers.
                • "DIRC: Increasing Indoor Wireless Capacity Using Directional Antennas" [pdf]
                  Xi Liu, Anmol Sheth, Michael Kaminsky, Konstantina Papagiannaki, Srini Seshan, Peter Steenkiste
                  SIGCOMM 2009
                  Uses steerable directional antennas to increase spatial reuse in indoor wireless networks.
                • "Geo-fencing: Confining Wi-Fi Coverage to Physical Boundaries" [pdf]
                  Anmol Sheth, Srini Seshan, David Wetherall
                  Pervasive 2009
                  Uses steerable directional antennas to contain Wi-Fi coverage to meaningful physical boundaries.
                • "Privacy Oracle: A System for Finding Application Leaks Using Black-box Differential Testing" [pdf]
                  Jaeyeon Jung, Anmol Sheth, Ben Greenstein, David Wetherall, Gabriel Maganis, Tadayoshi Kohno
                  CCS 2008
                  Reports on application leaks of user information via network traffic analysis.
                • "WiLDNet: Design and Implementation of High Performance WiFi Based Long Distance Networks" [pdf]
                  Rabin Patra, Sergiu Nedevschi, Sonesh Surana, Anmol Sheth, Lakshminarayanan Subramanian, Eric Brewer
                  NSDI 2007
                  Link and MAC layer modifications essential to provide high throughput over multi-hop long distance WiFi networks.
                • "Packet Loss Characterization in WiFi-based Long Distance Networks" [pdf]
                  Anmol Sheth, Sergiu Nedevschi, Rabin Patra, Sonesh Surana, Lakshminarayanan Subramanian, Eric Brewer,
                  Infocom 2007
                  Measurement study that identifies external interference as dominant source of packet loss in WiLD links.
                • "Senslide: a distributed landslide prediction system" [pdf]
                  Anmol Sheth, Chandramohan Thekkath, Prakshep. Mehta, K. Tejaswi , C. Parekh, T. N. Singh , Uday Desai
                  ACM SIGOPS 2007
                  System that uses a network of low-cost strain sensors to predict landslides.