HACCLE: metaprogramming for secure multi-party computation

Bao, Yuyan; Sundararajah, Kirshanthan; Malik, Raghav; Ye, Qianchuan; Wagner, Christopher; Jaber, Nouraldin; Wang, Fei; Ameri, Mohammad Hassan; Lu, Daihui; Seto, Alexander; Delaware, Benjamin; Samanta, Roopsha; Kate, Aniket; Garman, Christina; Blocki, Jeremiah; Létourneau, Pierre-David; Meister, Benoit; Springer, Jonathan; Rompf, Tiark; Kulkarni, Milind

doi:10.1145/3486609.3487205

Cited by 4 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For discrete device integration, a separate MPC program is generated and loaded to the chip; for CPU extension, the MPC instructions are embedded into the original CPU program. We can let programmers manually write short code pieces or leverage existing MPC program compilers (e.g., [5,37,53,90]) and add our multiplicand caching optimization ( §4.5).…”

Section: Put It Altogether: the Ppmlac Architecturementioning

confidence: 99%

Ppmlac

Zhou¹,

Gao

2022

Proceedings of the 49th Annual International Symposium on Computer Architecture

View full text Add to dashboard Cite

Privacy issue is a main concern restricting data sharing and crossorganization collaborations. While Privacy-Preserving Machine Learning techniques such as Multi-Party Computations (MPC), Homomorphic Encryption, and Federated Learning are proposed to solve this problem, no solution exists with both strong security and high performance to run large-scale, complex machine learning models. This paper presents PPMLAC, a novel chipset architecture to accelerate MPC, which combines MPC's strong security and hardware's high performance, eliminates the communication bottleneck from MPC, and achieves several orders of magnitudes speed up over software-based MPC. It is carefully designed to only rely on a minimum set of simple hardware components in the trusted domain, thus is robust against side-channel attacks and malicious adversaries. Our FPGA prototype can run mainstream large-scale ML models like ResNet in near real-time under a practical network environment with non-negligible latency, which is impossible for existing MPC solutions. CCS CONCEPTS• Hardware → Hardware accelerators; • Security and privacy → Hardware-based security protocols; Privacy-preserving protocols.

show abstract

Section: Put It Altogether: the Ppmlac Architecturementioning

confidence: 99%

Ppmlac

Zhou¹,

Gao

2022

Proceedings of the 49th Annual International Symposium on Computer Architecture

View full text Add to dashboard Cite

show abstract

Taype: A Policy-Agnostic Language for Oblivious Computation

Delaware

2023

Proc. ACM Program. Lang.

View full text Add to dashboard Cite

Secure multiparty computation (MPC) allows for joint computation over private data from multiple entities, usually backed by powerful cryptographic techniques that protect sensitive data. Several high-level programming languages have been proposed to make writing MPC applications accessible to non-experts. These languages typically require developers to enforce security policies within the logic of the secure application itself, making it difficult to update security requirements, or to experiment with different policies. This paper presents the design and implementation of Taype, a language that permits security concerns to be decoupled from the program logic. To do so, Taype provides the first implementation of oblivious algebraic data types and tape semantics, two language features recently proposed by a core calculus for oblivious computation, λ OADT + . We evaluate our implementation of Taype on a range of benchmarks, demonstrating its ability to encode a range of security polices for a rich class of data types.

show abstract

Taypsi: Static Enforcement of Privacy Policies for Policy-Agnostic Oblivious Computation

Ye,

Delaware

2024

Proc. ACM Program. Lang.

View full text Add to dashboard Cite

Secure multiparty computation (MPC) techniques enable multiple parties to compute joint functions over their private data without sharing that data with other parties, typically by employing powerful cryptographic protocols to protect individual's data. One challenge when writing such functions is that most MPC languages force users to intermix programmatic and privacy concerns in a single application, making it difficult to change or audit a program's underlying privacy policy. Prior policy-agnostic MPC languages relied on dynamic enforcement to decouple privacy requirements from program logic. Unfortunately, the resulting overhead makes it difficult to scale MPC applications that manipulate structured data. This work proposes to eliminate this overhead by instead transforming programs into semantically equivalent versions that statically enforce user-provided privacy policies. We have implemented this approach in a new MPC language, called Taypsi; our experimental evaluation demonstrates that the resulting system features considerable performance improvements on a variety of MPC applications involving structured data and complex privacy policies.

show abstract

HACCLE: metaprogramming for secure multi-party computation

Cited by 4 publications

References 42 publications

Ppmlac

Ppmlac

Taype: A Policy-Agnostic Language for Oblivious Computation

Taypsi: Static Enforcement of Privacy Policies for Policy-Agnostic Oblivious Computation

Contact Info

Product

Resources

About