Publications

Sanjay Kariyappa, Leonidas Tsepenekas, Freddy Lécué, Daniele Magazzeni (2024). SHAP@ k: Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features. Proceedings of the AAAI Conference on Artificial Intelligence.
PDF Cite
Sanjay Kariyappa, Freddy Lécué, Saumitra Mishra, Christopher Pond, Daniele Magazzeni, Manuela Veloso (2024). Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions. International Conference on Machine Learning.
PDF Cite
Trishita Tiwari, Suchin Gururangan, Chuan Guo, Weizhe Hua, Sanjay Kariyappa, Udit Gupta, Wenjie Xiong, Kiwan Maeng, Hsien-Hsin S Lee, G Edward Suh (2024). Information flow control in machine learning through modular model architecture. 33rd USENIX Security Symposium (USENIX Security 24).
PDF Cite Video
Sikha Pentyala, Shubham Sharma, Sanjay Kariyappa, Freddy Lecue, Daniele Magazzeni (2023). Privacy-Preserving Algorithmic Recourse. arXiv preprint arXiv:2311.14137.
PDF Cite
Sanjay Kariyappa, Moinuddin K Qureshi (2023). Exploit: Extracting private labels in split learning. 2023 IEEE conference on secure and trustworthy machine learning (SaTML).
PDF Cite Video
Sanjay Kariyappa, Chuan Guo, Kiwan Maeng, Wenjie Xiong, G Edward Suh, Moinuddin K Qureshi, Hsien-Hsin S Lee (2023). Cocktail party attack: Breaking aggregation-based privacy in federated learning using independent component analysis. International Conference on Machine Learning.
PDF Cite Code
Kiwan Maeng, Chuan Guo, Sanjay Kariyappa, G Edward Suh (2023). Bounding the invertibility of privacy-preserving instance encoding using fisher information. Advances in Neural Information Processing Systems.
PDF Cite Code
Sanjay Kariyappa, Ousmane Dia (2021). Semantics Preserving Adversarial Examples.
PDF Cite
Sanjay Kariyappa, Atul Prakash, Moinuddin K Qureshi (2021). Protecting dnns from theft using an ensemble of diverse models. International Conference on Learning Representations.
PDF Cite
Sanjay Kariyappa, Hsinyu Tsai, Katie Spoon, Stefano Ambrogio, Pritish Narayanan, Charles Mackin, An Chen, Moinuddin Qureshi, Geoffrey W Burr (2021). Noise-resilient DNN: tolerating noise in PCM-based AI accelerators via noise-aware training. IEEE Transactions on Electron Devices.
PDF Cite