REVIEW 7 cited by
FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high capacity networks such as VGG16 (ii) it supports batch normalization which is important for training complex networks such as AlexNet (iii) Falcon guarantees security with abort against malicious adversaries, assuming an honest majority (iv) Lastly, Falcon presents new theoretical insights for protocol design that make it highly efficient and allow it to outperform existing secure deep learning solutions. Compared to prior art for private inference, we are about 8x faster than SecureNN (PETS'19) on average and comparable to ABY3 (CCS'18). We are about 16-200x more communication efficient than either of these. For private training, we are about 6x faster than SecureNN, 4.4x faster than ABY3 and about 2-60x more communication efficient. Our experiments in the WAN setting show that over large networks and datasets, compute operations dominate the overall latency of MPC, as opposed to the communication.
Forward citations
Cited by 7 Pith papers
-
CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation
An MPC-ML compiler that modularizes and auto-tunes operator approximations, delivering 1.2–1.8x speedups over an optimized baseline under user-set accuracy bounds.
-
Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity
Comet accelerates MPC-based private LLM inference by securely predicting and skipping zero-valued neuron activations, achieving up to 2.6x speedup with about 1.5% accuracy loss.
-
Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction
Latent diffusion models can reconstruct recognizable images from deep-layer DNN features, and text or temporal priors further improve reconstruction quality.
-
CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference
A three-party framework that customizes binarized neural networks with distillation and separable convolutions to speed up privacy-preserving inference.
-
Towards Efficient Privacy-Preserving Machine Learning: A Systematic Review from Protocol, Model, and System Perspectives
A structured survey of PPML efficiency optimizations, grouped into protocol, model, and system levels, with comparisons and future directions.
-
EVA-S2PMLP: Secure and Scalable Two-Party MLP via Spatial Transformation
EVA-S2PMLP proposes secure two-party MLP protocols by splitting inputs into shares and masking matrices, but its base multiplication protocol returns shares whose sum is C_std + A times the masked B, not A times B.
-
A Survey of Secure Semantic Communications
A comprehensive survey of security and privacy challenges in semantic communication, categorized by the SemCom life cycle and paired with available defense technologies.
Discussion (0). Continue with ORCID to comment.