| 2026 | DATE | Late Breaking Results: Input Loss Curvature as a Predictor of Sample Vulnerability to Hardware-Noise. | Deepika Sharma, Deepak Ravikumar, Chih-Hsing Ho, Sangamesh Kodge, Kaushik Roy |
| 2025 | AAAI | SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness. | Sangamesh Kodge, Deepak Ravikumar, Gobinda Saha, Kaushik Roy |
| 2025 | CVPR | Improved Out-of-Distribution Detection with Additive Angular Margin Loss. | Deepak Ravikumar, Efstathia Soufleri, Kaushik Roy |
| 2025 | ICML | Towards Memorization Estimation: Fast, Formal and Free. | Deepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi, Kaushik Roy |
| 2025 | IOLTS | Building Resilient AI: Strengthening Data, Security, and Robustness in Neural Networks. | Deepak Ravikumar, Jimmy Gammell, Kaushik Roy |
| 2024 | ICML | Memorization Through the Lens of Curvature of Loss Function Around Samples. | Isha Garg, Deepak Ravikumar, Kaushik Roy |
| 2024 | ICML | Unveiling Privacy, Memorization, and Input Curvature Links. | Deepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi, Kaushik Roy |