Publications

117 results for Data and AI Security

Think 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 paper
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
- - Ivoline Ngong
  - Swanand Ravindra Kadhe
  - et al.
- 2025
- ACL 2025
Paper
KITE+: 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 paper
PATHE: A Privacy-Preserving Mass Spectrometry Database Pattern Search Platform with Fully Homomorphic Encryption
- - Xuan Wang
  - Minxuan Zhou
  - et al.
- 2025
- DAC 2025
Poster
IBM’s SARA SoC/SiP Project: Application-Driven High Level View
- - Pradip Bose
- 2025
- ISCA 2025
Workshop paper
A Near-DRAM Accelerator for Compiler-Generated Fully Homomorphic Encryption Applications
- - Alper Buyuktosunoglu
- 2025
- ISCA 2025
Workshop paper
Security and Resilience Challenges in AI-Centric Systems
- - Naorin Hossain
  - Karthik Swaminathan
  - et al.
- 2025
- ISCA 2025
Tutorial
Distributed Confidential AI Agents
- - Michael Le
  - Julian James Stephen
- 2025
- Confidential Computing Summit 2025
Talk
Challenges and Remedies of Domain-Specific Classifiers as LLM Guardrails: Self-Harm as a Case Study
- - Bing Zhang
  - Guang-Jie Ren
- 2025
- NAACL 2025
Short paper
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
- - Aladin Djuhera
  - Swanand Ravindra Kadhe
  - et al.
- 2025
- ICLR 2025
Workshop paper