Data Forging Is Harder Than You Think
- 2024
- ICLR 2024
Publications
Date
Featured collections
Popular topics
10 results for Swanand Ravindra Kadhe
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
- Ivoline Ngong
- Swanand Ravindra Kadhe
- et al.
- 2024
- NeurIPS 2024
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
- Swanand Ravindra Kadhe
- Farhan Ahmed
- et al.
- 2024
- ICML 2024
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks
- Shuli Jiang
- Swanand Ravindra Kadhe
- et al.
- 2023
- NeurIPS 2023
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs
- 2023
- NeurIPS 2023
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models
- Nathalie Baracaldo Angel
- Farhan Ahmed
- et al.
- 2023
- S&P 2023
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final Model
- 2022
- NeurIPS 2022
Federated Unlearning: How to Efficiently Erase a Client in FL?
- 2022
- ICML 2022
Using Large Language Models to protect information search in Multi-Domain Operations
- Dinesh Verma
- David Beymer
- et al.
- 2024
- SPIE DCS 2024
Robust Learning Protocol for Federated Tumor Segmentation Challenge
- 2022
- MICCAI 2022