2 papers
cs.CR2026
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
Pritam Dash, Tongyu Ge, Aditi Jain +2
Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory introduces the risk of memory…
cs.CR2025
Towards Privacy-Preserving Split Learning: Destabilizing Adversarial Inference and Reconstruction Attacks in the Cloud
Griffin Higgins, Roozbeh Razavi-Far, Xichen Zhang +3
This work aims to provide both privacy and utility within a split learning framework while considering both forward attribute inference and backward reconstruction attacks. To addr…