arxiv:2505.18773
i
iliashum
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
Strong Membership Inference Attacks on Massive Datasets and (Moderately)
Large Language Models
authored
a paper
5 days ago
Architectural Backdoors for Within-Batch Data Stealing and Model
Inference Manipulation
commented on
a paper
6 days ago
Architectural Backdoors for Within-Batch Data Stealing and Model
Inference Manipulation
Organizations
None yet
models
0
None public yet
datasets
0
None public yet