Tagged articles

Privacy-Preserving Machine Learning

3 articles · Page 1 of 1

Jun 18, 2026 · Artificial Intelligence

Can DP‑SGD’s Toughest Clip Threshold Auto‑Adjust? Inside the SlaClip Method

The article presents SlaClip, an adaptive gradient‑clipping technique for differential‑privacy SGD that leverages the slack between gradient norms and the clipping threshold as a privacy‑preserving indicator, eliminating extra privacy queries and dynamically adjusting the clipping bound, with experiments showing competitive accuracy across datasets and budgets.

Adaptive ClippingDP-SGDDifferential Privacy

0 likes · 8 min read

Can DP‑SGD’s Toughest Clip Threshold Auto‑Adjust? Inside the SlaClip Method

AntTech

Nov 12, 2024 · Artificial Intelligence

Rhombus: Fast Homomorphic Matrix‑Vector Multiplication for Secure Two‑Party Inference – Paper Overview and Live Presentation

The article introduces the Rhombus protocol, a fast homomorphic matrix‑vector multiplication scheme that reduces ciphertext rotations and achieves O(1) communication complexity, enabling efficient privacy‑preserving two‑party inference, and announces a live streaming session where the first author will discuss its technical details and experimental results.

Homomorphic EncryptionPrivacy-Preserving Machine LearningRhombus protocol

0 likes · 3 min read

Rhombus: Fast Homomorphic Matrix‑Vector Multiplication for Secure Two‑Party Inference – Paper Overview and Live Presentation

AntTech

May 12, 2022 · Artificial Intelligence

Privacy-Preserving Cross-Domain Recommendation via Differential Privacy and Subspace Embedding

The article reviews a TheWebConf 2022 paper that introduces a two‑stage framework combining differential‑privacy‑based random subspace publishing (using Johnson‑Lindenstrauss and sparse‑aware transforms) with asymmetric deep models to achieve accurate, privacy‑preserving cross‑domain recommendation, and discusses broader differential‑privacy applications.

Privacy-Preserving Machine LearningRecommendation SystemsSubspace Embedding

0 likes · 9 min read

Privacy-Preserving Cross-Domain Recommendation via Differential Privacy and Subspace Embedding