GPU-Accelerated Secure Inference for Drug--Target Interaction Prediction
Organizations: University of Washington Tacoma, Tacoma, Washington, USA
Abstract
Deep learning models that predict drug--target interactions (DTI) can speed up drug discovery, but the candidate drugs they score are valuable intellectual property that their owners cannot reveal. Secure multiparty computation (MPC) lets two servers compute a prediction on a secret-shared drug, without either server learning the drug. However, secure inference of deep models is slow. Non-linear operations require communication between the servers, and MPC arithmetic does not map naturally to GPUs. In this paper, we present our solution to Track~III of the iDASH 2026 privacy and security competition, which asked for fast two-party secure DTI inference on GPUs. Our solution is built on the co-design of MPC-friendly models and MPC protocols. On the model side, we design SlimDTA, a DTI model that reduces the operations on the secret drug, and in particular the non-linear operations that require communication. On the protocol side, we build a GPU framework that evaluates the linear layers with additive secret sharing and the non-linear layers with function secret sharing, including a custom CUDA kernel for the comparisons. Our solution won first place in the competition, at under 10,ms per prediction on average, and its secure predictions match the plaintext model to within 0.02%.
Figures & tables
| Symbol | Meaning |
|---|---|
| the two servers | |
| the ring of integers modulo ; we use | |
| number of fractional bits in fixed-point encoding; we use | |
| additive secret sharing of ; server holds | |
| most significant bit of ; equals 1 if and only if is negative | |
| , | a random mask and a masked value |
| Protocol | Description | Rounds | Bits sent | Reference |
| Basic primitives | ||||
| , , | addition, and operations with a public constant | 0 | 0 | Eqs. ( 4 )–( 6 ) |
| division by after a product | 0 | 0 | Mohassel and Zhang (2017) | |
| reveal to both servers | 1 | — | ||
| product with a Beaver triple | 1 | Beaver (1991) | ||
| XOR shares of , by FSS | 1 | Boyle et al. (2021) | ||
| DeepDTA ( Öztürk et al., 2018 ) | DeepDTAGen (affinity) | SlimDTA | |
|---|---|---|---|
| Drug input | SMILES | molecular graph | SMILES |
| Drug encoder | 3 conv (32, 64, 96) | 3 graph conv | 3 conv (16, 32, 48) |
| Protein encoder | 3 conv (32, 64, 96) | gated conv, flattened into | 3 dilated conv (32, 64, 96) |
| a 1.3M-parameter linear layer | |||
| Head | 3 FC layers | 4 FC layers | 2 FC layers |
| Parameters | 1.9M | 3.58M | 0.80M |
| Team | BindingDB (1,000 samples) | BindingDB (10,000 samples) | Davis (1,000 samples) |
|---|---|---|---|
| PPMLHuskies (ours) | 9.2 s | 91.5 s | 8.1 s |
| Team A | 14.4 s | 106.1 s | 9.5 s |
| Team B | 14.0 s | 164.6 s | 12.7 s |
| Team C | 2,486.0 s | 25,463.5 s | 2,518.9 s |
| Ours, per sample | 9.2 ms | 9.2 ms | 8.1 ms |
| Ours, speedup over the next fastest | 1.52 | 1.16 | 1.17 |
| Online time per sample (ms) | Ours, split (ms) | ||||
|---|---|---|---|---|---|
| Batch | FSS + CUDA (ours) | FSS + PyTorch | Bit decomposition | Communication | Computation |
| 16 | 67.8 | 293.4 | 386.3 | 10.6 | 56.9 |
| 64 | 20.9 | 72.8 | 252.0 | 8.9 | 12.0 |
| 256 | 11.5 | 33.7 | 223.4 | 8.6 | 3.0 |
| 512 | 10.0 | 32.1 | 219.0 | 8.5 | 1.5 |
| 1,024 | 9.5 | 34.7 | out of memory | 8.6 | 0.9 |
| Secret inputs | Comparisons by | Comparisons per sample | Rounds | MB per sample |
|---|---|---|---|---|
| drug, protein, weights | bit decomposition | 1,727 | 481 | |
| drug, protein, weights | FSS | 90 | 41.5 | |
| drug only | bit decomposition | 12,624 | 1,549 | 13.2 |
| drug only | FSS (ours) | 12,624 | 37 | 0.505 |
| Layer | Output | Secret multiply-adds | Comparisons | Rounds |
|---|---|---|---|---|
| Embedding | 707,200 | 0 | 0 | |
| Conv 1 (kernel 4) and ReLU | 671,744 | 1,312 | 3 | |
| Conv 2 (kernel 4) and ReLU | 161,792 | 2,528 | 3 | |
| Conv 3 (kernel 4) and ReLU | 466,944 | 3,648 | 3 | |
| Global max pool | 0 | 3,600 | 21 | |
| FC 1, drug part ( ), and ReLU | 49,152 | 1,024 | 3 |
Secure Multi-Party Computation
Secure multi-party computation lets organizations jointly analyze private data without revealing their inputs to one another.
See all 24 papers