Kadhe, Swanand

9 publications

ICLRW 2025 SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging Aladin Djuhera, Swanand Kadhe, Farhan Ahmed, Syed Zawad, Holger Boche

ICLRW 2024 Data Forging Is Harder than You Think Mohamed Suliman, Swanand Kadhe, Anisa Halimi, Douglas Leith, Nathalie Baracaldo, Ambrish Rawat

NeurIPSW 2024 Protecting Users from Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents Ivoline C. Ngong, Swanand Kadhe, Hao Wang, Keerthiram Murugesan, Justin D. Weisz, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy

ICMLW 2024 Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs Swanand Kadhe, Farhan Ahmed, Dennis Wei, Nathalie Baracaldo, Inkit Padhi

NeurIPSW 2023 FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs Swanand Kadhe, Anisa Halimi, Ambrish Rawat, Nathalie Baracaldo

NeurIPSW 2023 Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks Shuli Jiang, Swanand Kadhe, Yi Zhou, Ling Cai, Nathalie Baracaldo

ICML 2023 LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning Timothy Castiglia, Yi Zhou, Shiqiang Wang, Swanand Kadhe, Nathalie Baracaldo, Stacy Patterson

NeurIPSW 2022 Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final Model Nathalie Baracaldo, Kevin Eykholt, Farhan Ahmed, Yi Zhou, Shriti Priya, Taesung Lee, Swanand Kadhe, Yusong Tan, Sridevi Polavaram, Sterling Suggs, Yuyang Gao, David Slater

NeurIPS 2021 Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation Divyansh Jhunjhunwala, Ankur Mallick, Advait Gadhikar, Swanand Kadhe, Gauri Joshi