LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
- Changsheng Wang
- Yihua Zhang
- et al.
- 2025
- AISec 2025
Workshop paper
Publications
120 results for Data and AI Security
Securing MCP-based Agent Workflows
- Grigoris Ntousakis
- Julian James Stephen
- et al.
- 2025
- SOSP 2025
Workshop paperAutomated Annotation Inference for MCP-based Agents
- Grigoris Ntousakis
- Julian James Stephen
- et al.
- 2025
- SOSP 2025
Workshop paperThink Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
- George Kour
- Itay Nakash
- et al.
- 2025
- ACL 2025
Conference paperProtecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
- Ivoline Ngong
- Swanand Ravindra Kadhe
- et al.
- 2025
- ACL 2025
PaperKITE+: A Knowledge Integration Platform to Support the Development of Multi-Modal, Large-Scale Data Analytics Applications with Alignment to Modern Data Protection Laws
- Rodrigo Ordonez-Hurtado
- Francesca Bonin
- et al.
- 2025
- ICDH 2025
Conference paperPATHE: A Privacy-Preserving Mass Spectrometry Database Pattern Search Platform with Fully Homomorphic Encryption
- Xuan Wang
- Minxuan Zhou
- et al.
- 2025
- DAC 2025
PosterA Near-DRAM Accelerator for Compiler-Generated Fully Homomorphic Encryption Applications
- 2025
- ISCA 2025
Workshop paperIBM’s SARA SoC/SiP Project: Application-Driven High Level View
- Pradip Bose
- 2025
- ISCA 2025
Workshop paperSecurity and Resilience Challenges in AI-Centric Systems
- 2025
- ISCA 2025
Tutorial