Associate Professor
Department of Computer Science
Virginia Tech

Google Scholar

Contact
Email: vbimal@vt.edu


Gilbert Place
Room #4302
220 Gilbert Street
Blacksburg, VA 24060
Phone: 540-231-8702

My research lies at the intersection of security, privacy, and AI, with a primary mission to ensure the safety and trustworthiness of emerging AI technologies.

My group focuses on three interconnected challenges in the era of Generative AI and Foundation Models:

  • Defending Against AI-Enabled Threats: Investigating how attackers leverage recent advances—such as multimodal LLMs—to generate harmful content or compromise systems.
  • Securing AI Infrastructure: Uncovering vulnerabilities in machine learning supply chains and model deployment to prevent adversarial attacks and backdoors.
  • AI for Defense: Leveraging the reasoning capabilities of modern AI to build more dynamic and resilient security protections.

I am a recipient of the Distinguished Paper Award (USENIX Security'25), Distinguished Paper Award (SOUPS 2014), Best Paper Award (COSN 2015), and the AI2000 Most Influential Scholar Award Honorable Mention for being among the top 100 most cited scholars in computer networking from 2009-2019.

I completed my Ph.D. in Computer Science at the Max Planck Institute for Software Systems. Before joining VT, I spent ~2 years as a Postdoc in SAND lab (at UCSB). Prior to that, I spent a year as a Researcher at Nokia Bell Labs, Stuttgart.

Our research is supported by CCI, NSF and 4-VA.

Latest Updates

September 2025: Serving as Track Co-chair (along with Dr. Franziska Boenisch) for the Machine Learning and Security track at AsiaCCS'26.
August 2025: New NSF SaTC Medium funding to address data challenges in ML-based security tasks using Generative AI.
July 2025: Promoted to Associate Professor with Tenure.
January 2025: Our NeuralCleanse work (IEEE S&P’19) is listed among the Normalized Top-100 Security Papers and also the Top-100 Security papers from 1980 to 2025.
August 2023: Invited to participate in the AI Technology Initiative organized by the Bipartisan Virginia Technology and Innovation Caucus. This initiative is to “explore opportunities, risks, and impacts associated with Artificial lntelligence (AI) and technology use in government processes and decision-making.”
July 2023: Our work on deepfake text detection (IEEE S&P'23 paper) was featured in a CACM article by Neil Savage.
February 2023: New NSF SaTC funding to study security of open-domain chatbots.

Publications

  • Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes
    Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde, Peng Gao, Mainack Mondal, Murtuza Jadliwala, and Bimal Viswanath.
    IEEE SaTML'26, Munich, Germany, March 2026. To Appear.
    Arxiv (coming soon) Code and dataset (coming soon)

  • Taming Data Challenges in ML-based Security Tasks: Lessons from Integrating Generative AI
    Shravya Kanchi, Neal Mangaokar, Aravind Cheruvu, Sifat Muhammad Abdullah, Shirin Nilizadeh, Atul Prakash, and Bimal Viswanath.
    ACM AsiaCCS'26, Bangalore, India, June 2026. To Appear.
    Arxiv Code and dataset

  • We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
    Joseph Spracklen, Raveen Wijewickrama, AHM Nazmus Sakib, Anindya Maiti, Bimal Viswanath, and Murtuza Jadliwala
    USENIX Security'25, Seattle, WA, August 2025.
    Arxiv Code and dataset Distinguished Paper Award

  • An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
    Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi, Taejoong Chung, Peng Gao, Murtuza Jadliwala and Bimal Viswanath
    IEEE S&P (Oakland) 2024, San Francisco, CA, May 2024.
    Arxiv Code and dataset

  • A First Look at Toxicity Injection Attacks on Open-domain Chatbots
    Connor Weeks (co-lead), Aravind Cheruvu (co-lead), Sifat Muhammad Abdullah, Shravya Kanchi, Daphne Yao, and Bimal Viswanath
    ACSAC 2023, Austin, Texas, December 2023.
    PDF Code and dataset

  • Deepfake Text Detection: Limitations and Opportunities
    Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah, Abdullah Rehman, Yoonjin Kim, Parantapa Bhattacharya, Mobin Javed, and Bimal Viswanath
    IEEE S&P (Oakland) 2023, San Francisco, CA, May 2023.
    PDF Code and dataset

  • T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
    Ahmadreza Azizi, Ibrahim Asadullah Tahmid, Asim Waheed, Neal Mangaokar, Jiameng Pu, Mobin Javed, Chandan K. Reddy and Bimal Viswanath
    USENIX Security'21, Online, August 2021
    PDF (arxiv) Video Code

  • Deepfake Videos in the Wild: Analysis and Detection
    Jiameng Pu (co-lead), Neal Mangaokar (co-lead), Lauren Kelly, Parantapa Bhattacharya, Kavya Sundaram, Mobin Javed, Bolun Wang, and Bimal Viswanath
    WWW'21, Online, April 2021
    PDF (arxiv) Video Deepfake dataset

  • NoiseScope: Detecting Deepfake Images in a Blind Setting
    Jiameng Pu, Neal Mangaokar, Bolun Wang, Chandan K. Reddy, and Bimal Viswanath
    ACSAC'20, Online, December 2020
    PDF BIBTEX Video Code

  • Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
    Neal Mangaokar, Jiameng Pu, Parantapa Bhattacharya, Chandan K. Reddy, and Bimal Viswanath
    IEEE EuroS&P 2020, Online, September 2020
    PDF BIBTEX Video

  • Throwing Darts in the Dark? Detecting Bots with Limited Data using Neural Data Augmentation
    Steve T.K. Jan, Qingying Hao, Tianrui Hu, Jiameng Pu, Sonal Oswal, Gang Wang, and Bimal Viswanath
    IEEE S&P (Oakland) 2020, Online, May 2020
    PDF BIBTEX

  • What Happens After You Leak Your Password: Understanding Credential Sharing on Phishing Sites
    Peng Peng, Chao Xu, Luke Quinn, Hang Hu, Bimal Viswanath, and Gang Wang
    ASIACCS 2019, Auckland, New Zealand, July 2019
    PDF BIBTEX

  • Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
    Bolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li, Bimal Viswanath, Haitao Zheng, and Ben Y. Zhao
    IEEE S&P (Oakland) 2019, San Francisco, CA, USA, May 2019
    PDF BIBTEX Code

  • With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning
    Bolun Wang, Yuanshun Yao, Bimal Viswanath, Haitao Zheng, and Ben Y. Zhao
    USENIX Security 2018, Baltimore, MD, USA, August 2018
    PDF BIBTEX Code

  • I Spy with My Little Eye: Analysis and Detection of Spying Browser Extensions
    Anupama Aggarwal, Bimal Viswanath, Liang Zhang, Saravana Kumar, Ayush Shah, and Ponnurangam Kumaraguru
    IEEE EuroS&P 2018, London, UK, April 2018
    PDF BIBTEX

  • Towards Reliable Application Deployment in the Cloud
    Ruichuan Chen, Istemi Ekin Akkus, Bimal Viswanath, Ivica Rimac and Volker Hilt
    CoNEXT 2017, Seoul, South Korea, December 2017
    PDF BIBTEX

  • Sieve: Actionable Insights from Monitored Metrics in Distributed Systems
    Jörg Thalheim, Antonio Rodrigues, Istemi Ekin Akkus, Pramod Bhatotia, Ruichuan Chen, Bimal Viswanath, Lei Jiao, Christof Fetzer
    Middleware 2017, Las Vegas, NV, USA, December 2017
    PDF BIBTEX Website Technical report

  • Complexity vs. Performance: Empirical Analysis of Machine Learning as a Service
    Yuanshun Yao, Zhujun Xiao, Bolun Wang, Bimal Viswanath, Haitao Zheng and Ben Y. Zhao
    IMC 2017, London, UK, November 2017
    PDF BIBTEX

  • Automated Crowdturfing Attacks and Defenses in Online Review Systems
    Yuanshun Yao, Bimal Viswanath, Jenna Cryan, Haitao Zheng and Ben Y. Zhao
    CCS 2017, Dallas, TX, USA, October 2017
    PDF BIBTEX

  • Strengthening Weak Identities Through Inter-Domain Trust Transfer
    Giridhari Venkatadri, Oana Goga, Changtao Zhong, Bimal Viswanath, Krishna P. Gummadi and Nishanth Sastry
    WWW 2016, Montreal, Canada, April 2016
    PDF BIBTEX

  • Strength in Numbers: Robust Tamper Detection in Crowd Computations
    Bimal Viswanath, M. Ahmad Bashir, M. Bilal Zafar, Simon Bouget, Saikat Guha, Krishna P. Gummadi, Aniket Kate, and Alan Mislove
    COSN 2015, Stanford University, CA, USA, November 2015
    PDF BIBTEX Best Paper Award

  • Towards Detecting Anomalous User Behavior in Online Social Networks
    Bimal Viswanath, Muhammad Ahmad Bashir, Mark Crovella, Saikat Guha, Krishna P. Gummadi, Balachander Krishnamurthy and Alan Mislove
    USENIX Security 2014, San Diego, CA, USA, August 2014
    PDF BIBTEX

  • Understanding and Specifying Social Access Control Lists
    Mainack Mondal, Yabing Liu, Bimal Viswanath, Krishna P. Gummadi and Alan Mislove
    SOUPS 2014, Menlo Park, CA, USA, July 2014
    PDF BIBTEX Distinguished Paper Award

  • Defending Against Large-scale Crawls in Online Social Networks
    Mainack Mondal, Bimal Viswanath, Allen Clement, Peter Druschel, Krishna P. Gummadi, Alan Mislove, and Ansley Post
    CoNEXT 2012, Nice, France, December 2012
    PDF BIBTEX

  • Keeping Information Safe from Social Networking Apps
    Bimal Viswanath, Emre Kıcıman, and Stefan Saroiu
    WOSN 2012, Helsinki, Finland, August 2012
    PDF BIBTEX

  • Canal: Scaling Social Network-based Sybil Tolerance Schemes
    Bimal Viswanath, Mainack Mondal, Krishna P. Gummadi, Alan Mislove, and Ansley Post
    EuroSys 2012, Bern, Switzerland, April 2012
    PDF BIBTEX

  • Understanding and Combating Link Farming in the Twitter Social Network
    Saptarshi Ghosh (co-primary author), Bimal Viswanath (co-primary author), Farshad Kooti, Naveen Kumar Sharma, Korlam Gautam, Fabricio Benevenuto, Niloy Ganguly, and Krishna P. Gummadi
    WWW 2012, Lyon, France, April 2012
    PDF BIBTEX

  • Exploring the Design Space of Social Network-based Sybil Defenses (Invited Paper)
    Bimal Viswanath, Mainack Mondal, Allen Clement, Peter Druschel, Krishna P. Gummadi, Alan Mislove, and Ansley Post
    COMSNETS 2012, Bangalore, India, January 2012
    PDF BIBTEX

  • Sharing Social Content from Home: A Measurement-driven Feasibility Study
    Massimiliano Marcon, Bimal Viswanath, Meeyoung Cha, and Krishna P. Gummadi
    NOSSDAV 2011, Vancouver, Canada, June 2011
    PDF BIBTEX

  • An Analysis of Social Network-based Sybil Defenses
    Bimal Viswanath, Ansley Post, Krishna P. Gummadi, and Alan Mislove
    SIGCOMM 2010, New Delhi, India, August 2010
    PDF BIBTEX

  • You Are Who You Know: Inferring User Profiles in Online Social Networks
    Alan Mislove, Bimal Viswanath, Krishna P. Gummadi, and Peter Druschel
    WSDM 2010, New York, NY, USA, February 2010
    PDF BIBTEX

  • On the Evolution of User Interaction in Facebook
    Bimal Viswanath, Alan Mislove, Meeyoung Cha, and Krishna P. Gummadi
    WOSN 2009, Barcelona, Spain, August 2009
    PDF Original PDF (with Errata) Errata Note BIBTEX

Students

I am delighted to work with the following students:

Current Students

PhD Students
  • Xavier Pleimling (Fall 2024 - Present)
    Published in IEEE SaTML'26
MS Students
  • Cameron Mraz (Fall 2025 - Present)
  • Brianna Detter (Fall 2025 - Present)
Undergraduate Students
  • Rudra Patel (Fall 2025 - Present)

Alumni

PhD Graduates
  • Sifat Muhammad Abdullah (2025)
    Published in IEEE SaTML'26, AsiaCCS'26, IEEE S&P'24, IEEE S&P'23, ACSAC'23
  • Jiameng Pu (2022)
    Published in IEEE S&P'23, USENIX Security'21, WWW'21, ACSAC'20, IEEE EuroS&P'20, IEEE S&P'20
  • Steve T.K. Jan (2020, co-advised with Gang Wang)
    Published in IEEE S&P'20
Master's Graduates
  • Nicholas Kong (2024)
  • Connor Weeks (2023)
    Published in ACSAC'23
  • Cristian Vives (2022)
  • Ahmadreza Azizi (2020)
    Published in USENIX Security'21
  • Tianrui Hu (2020, co-advised with Gang Wang)
    Published in IEEE S&P'20.
Undergraduate Students
  • Neal Mangaokar (2020)
    Published in IEEE EuroS&P'20, ACSAC'20, USENIX Security'21, WWW'21.
  • Lauren Kelly (2020)
    Published in WWW'21.
  • Kavya Sundaram
    Published in WWW'21
  • Abdullah Rehman
    Published in IEEE S&P'23

Selected Service

  • CCS (PC: 2024, 2023, 2022, 2021)
  • USENIX Security (PC: 2025, 2022, 2021, 2020)
  • NDSS (PC: 2021, 2020)
  • IMC (PC: 2019)
  • ACSAC (PC: 2021, 2020, 2019)
  • ICWSM (PC: 2018, 2017, 2016, 2015)

Teaching

  • CS6604: Foundation Models and Security
    Virginia Tech, Spring 2024.
  • CS5914: Security Risks of Generative AI
    Virginia Tech, Fall 2023.
  • CS4274: Secure Computing Capstone
    Virginia Tech, Fall 2021, Spring 2023, Spring 2024.
  • CS5914: Defending Against ML-powered Adversaries
    Virginia Tech, Fall 2022.
  • CS6604: Hot Topics in Security and AI
    Virginia Tech, Spring 2020, Spring 2022.
  • CS5984: Security Analytics
    Virginia Tech, Spring 2019, Spring 2021.
  • CS4254: Network Architecture & Programming
    Virginia Tech, Fall 2018, Fall 2019, Fall 2020.
  • Security and Privacy in Social Computing Systems
    Saarland University, Summer 2013.

Selected News