Marco Di Gennaro
@marcodige.bsky.social
📤 12
📥 10
📝 8
PhD Student @PoliMi, Security & Privacy of Machine and Federated Learning Researcher, 26, Italy.
pinned post!
📣 Our paper “On the (In)Security of Loading Machine Learning Models” has been accepted at IEEE S&P 2026 (13% acceptance rate this cycle). (1/5) 👇 Preprint:
arxiv.org/abs/2509.06703
#ieeesp
#ieeesp26
#ieee
#cybersecurity
#softwaresecurity
#aisecurity
#machinelearning
#ml
#zeroday
25 days ago
1
9
4
📣 Our paper “On the (In)Security of Loading Machine Learning Models” has been accepted at IEEE S&P 2026 (13% acceptance rate this cycle). (1/5) 👇 Preprint:
arxiv.org/abs/2509.06703
#ieeesp
#ieeesp26
#ieee
#cybersecurity
#softwaresecurity
#aisecurity
#machinelearning
#ml
#zeroday
25 days ago
1
9
4
🚨 Our PoPETS 2025 work, "TimberStrike," finds that federated tree models are vulnerable to privacy leakage via dataset reconstruction. See you in Washington D.C. in July! 📄 Preprint:
www.arxiv.org/abs/2506.07605
#FederatedLearning
#Privacy
#PoPETS
loading . . .
TimberStrike: Dataset Reconstruction Attack Revealing Privacy Leakage in Federated Tree-Based Systems
Federated Learning has emerged as a privacy-oriented alternative to centralized Machine Learning, enabling collaborative model training without direct data sharing. While extensively studied for neura...
https://www.arxiv.org/abs/2506.07605
10 months ago
1
4
2
you reached the end!!
feeds!
log in
