Yuvaraj Govindarajulu

Logo

Personal Profile and Blog

View My GitHub Profile

Publications

(For latest publications, visit: Google Scholar)

Conference Papers and Posters

  1. Arjun, E. R. R., Kulkarni, P., Govindarajulu, Y., Shah, H., & Parmar, M. (2024). Evasion Attacks on Object Detection Models using Attack Transferability. In 2024 IEEE Secure Development Conference (SecDev) (pp. 28–34). IEEE.

  2. Shah, P., Govindarajulu, Y., Kulkarni, P., & Parmar, M. (2024). Enhancing TinyML Security: Study of Adversarial Attack Transferability. Conference-TinyML EMEA Innovation Forum, Milan June 2024, . Conference Paper

  3. Shah, H., Aravindhan, G., Kulkarni, P., Govindarajulu, Y., & Parmar, M. (2023). Data-Free Model Extraction Attacks in the Context of Object Detection. In International Conference on Computer Vision Systems (pp. 391–402). Springer Nature Switzerland, Cham.

  4. Bhardwaj, G., Govindarajulu, Y., Narayanan, S., Kulkarni, P., & Parmar, M. (2023). On the notion of Hallucinations from the lens of Bias and Validity in Synthetic CXR Images. NeurIPS Workshop - Medical Imaging meets NeurIPS. Workshop Publication-Abstract

  5. Shah, P., Govindarajulu, Y., Kulkarni, P., & Parmar, M. (2023). Exploring AI Attacks on Hardware Accelerated Targets. In 2023 IEEE 2nd International Conference on Data, Decision and Systems (ICDDS) (pp. 1–6). IEEE.

  6. Aravindhan, G., Govindarajulu, Y., Kulkarni, P., & Parmar, M. (2023). BAPFAS: Black Box Approximated Fast Sign Adversarial Samples. In 2023 IEEE 2nd International Conference on Data, Decision and Systems (ICDDS) (pp. 1–6). IEEE.

Talks

  1. Eine praktische Lösung für die vertrauenswürdige Nutzung von LLMs in Unternehmen [German], BSI 20. IT Security Congress, Germany · May 7, 2024, Kongress Publication - Page 186

  2. Die Notwendigkeit, KI-Assets zu sichern [German], Forum IT-SA Expo 2023, Nurnberg · Oct 10, 2023, Kongress

  3. Navigating the Generative AI Revolution: Ensuring Compliance and Security in the Era of LLMs with Guardrails [Webinar: English], AI Infrastructure Alliance · Sep 15, 2023, Webinar

  4. Protect your raison d’etre – Artificial Intelligence [English], Jan 5, 2023, Workshop on Trustworthy AI, Microsoft Research, Bengaluru, India

  5. Attacks on Tiny Intelligence (TinyMLSec), TinyML Asia 2022 · Nov 29, 2022 Conference, Publication

  6. Attacks on Tiny Intelligence, AIVillage, DEFCON30 · Aug 14, 2022, Conference

Preprints

  1. Govindarajulu, Y., Amballa, A., Kulkarni, P., & Parmar, M. (2023). Targeted Attacks on Timeseries Forecasting. arXiv preprint arXiv:2301.11544. https://arxiv.org/abs/2301.11544

  2. Pankajakshan, R., Biswal, S., Govindarajulu, Y., & Gressel, G. (2024). Mapping LLM Security Landscapes: A Comprehensive Stakeholder Risk Assessment Proposal. arXiv preprint arXiv:2403.13309. https://arxiv.org/abs/2403.13309

  3. Khazanchi, V., Kulkarni, P., Govindarajulu, Y., & Parmar, M. (2024). MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception. arXiv preprint arXiv:2404.15656. https://arxiv.org/abs/2404.15656

  4. Sendhil Kumar, S., Govindarajulu, Y., Kulkarni, P., & Parmar, M. (2024). VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces. arXiv e-prints, arXiv–2408. https://arxiv.org/abs/2408

  5. Govindarajulu, Y., & Kumar, R. R. R. (2020). Gesture Recognition based on Long-Short Term Memory Cells using Smartphone IMUs. arXiv preprint arXiv:2308.11642. https://arxiv.org/abs/2308.11642