An official website of the United States government
The growing popularity of Machine Learning (ML) has led to its deployment in various sensitive domains, which has resulted in significant research focused on ML security and privacy. However, in some applications, such as Augmented/Virtual Reality, integrity verification of the outsourced ML tasks is more critical–a face that has not received much attention. Existing solutions, such as multi-party computation and proof-based systems, impose significant computation overhead, which makes them unfit for real-time applications. We propose Fides, a novel framework for real-time integrity validation of ML-as-a-Service (MLaaS) inference. Fides features a novel and efficient distillation technique–Greedy Distillation Transfer Learning–that dynamically distills and fine-tunes a space and compute-efficient verification model for verifying the corresponding service model while running inside a trusted execution environment. Fides features a client-side attack detection model that uses statistical analysis and divergence measurements to identify, with a high likelihood, if the service model is under attack. Fides also offers a re-classification functionality that predicts the original class whenever an attack is identified. We devised a generative adversarial network framework for training the attack detection and re-classification models. The evaluation shows that Fides achieves an accuracy of up to 98% for attack detection and 94% for re-classification.
more »
« less
Real-time HEP analysis with funcX, a high-performance platform for function as a service
We explore how the function as a service paradigm can be used to address the computing challenges in experimental high-energy physics at CERN. As a case study, we use funcX—a high-performance function as a service platform that enables intuitive, flexible, efficient, and scalable remote function execution on existing infrastructure—to parallelize an analysis operating on columnar data to aggregate histograms of analysis products of interest in real-time. We demonstrate efficient execution of such analyses on heterogeneous resources.
more »
« less
- PAR ID:
- 10223812
- Editor(s):
- Doglioni, C.; Kim, D.; Stewart, G.A.; Silvestris, L.; Jackson, P.; Kamleh, W.
- Date Published:
- Journal Name:
- EPJ Web of Conferences
- Volume:
- 245
- ISSN:
- 2100-014X
- Page Range / eLocation ID:
- 07046
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Biscarat, C.; Campana, S.; Hegner, B.; Roiser, S.; Rovelli, C.I.; Stewart, G.A. (Ed.)In High Energy Physics facilities that provide High Performance Computing environments provide an opportunity to efficiently perform the statistical inference required for analysis of data from the Large Hadron Collider, but can pose problems with orchestration and efficient scheduling. The compute architectures at these facilities do not easily support the Python compute model, and the configuration scheduling of batch jobs for physics often requires expertise in multiple job scheduling services. The combination of the pure-Python libraries pyhf and funcX reduces the common problem in HEP analyses of performing statistical inference with binned models, that would traditionally take multiple hours and bespoke scheduling, to an on-demand (fitting) “function as a service” that can scalably execute across workers in just a few minutes, offering reduced time to insight and inference. We demonstrate execution of a scalable workflow using funcX to simultaneously fit 125 signal hypotheses from a published ATLAS search for new physics using pyhf with a wall time of under 3 minutes. We additionally show performance comparisons for other physics analyses with openly published probability models and argue for a blueprint of fitting as a service systems at HPC centers.more » « less
-
Joe Calandrino and Carmela Troncoso (Ed.)As service providers are moving to the cloud, users are forced to provision sensitive data to the cloud. Confidential computing leverages hardware Trusted Execution Environment (TEE) to protect data in use, no longer requiring users’ trust to the cloud. The emerging service model, Confidential Computing as a Service (CCaaS), is adopted by service providers to offer service similar to the Function-as-a-Serivce manner. However, privacy concerns are raised in CCaaS, especially in multi-user scenarios. CCaaS need to assure the data providers that the service does not leak their privacy to any unauthorized parties and clear their data after the service. To address such privacy concerns with security guarantees, we first formally define the security objective, Proof of Being Forgotten (PoBF), and prove under which security constraints PoBF can be satisfied. Then, these constraints serve as guidelines in the implementation of the PoBF-compliant Framework (PoCF). PoCF consists of a generic library for different hardware TEEs, CCaaS prototype enclaves, and a verifier to prove PoBF-compliance. PoCF leverages Rust’s robust type system and security features, to construct a verified state machine with privacy-preserving contracts. Last, the experiment results show that the protections introduced by PoCF incur minor runtime performance overhead.more » « less
-
Interactive web-based applications play an important role for both service providers and consumers. However, web applications tend to be complex, produce high-volume data, and are often ripe for attack. Attack analysis and remediation are complicated by adversary obfuscation and the difficulty in assembling and analyzing logs. In this work, we explore the web application analysis task through log file fusion, distillation, and visualization. Our approach consists of visualizing the logs of web and database traffic with detailed function execution traces. We establish causal links between events and their associated behaviors. We evaluate the effectiveness of this process using data volume reduction statistics, user interaction models, and usage scenarios. Across a set of scenarios, we find that our techniques can filter at least 97.5% of log data and reduce analysis time by 93-96%.more » « less
-
As the popularity of quantum computing continues to grow, efficient quantum machine access over the cloud is critical to both academic and industry researchers across the globe. And as cloud quantum computing demands increase exponentially, the analysis of resource consumption and execution characteristics are key to efficient management of jobs and resources at both the vendor-end as well as the client-end. While the analysis and optimization of job / resource consumption and management are popular in the classical HPC domain, it is severely lacking for more nascent technology like quantum computing.This paper proposes optimized adaptive job scheduling to the quantum cloud taking note of primary characteristics such as queuing times and fidelity trends across machines, as well as other characteristics such as quality of service guarantees and machine calibration constraints. Key components of the proposal include a) a prediction model which predicts fidelity trends across machine based on compiled circuit features such as circuit depth and different forms of errors, as well as b) queuing time prediction for each machine based on execution time estimations.Overall, this proposal is evaluated on simulated IBM machines across a diverse set of quantum applications and system loading scenarios, and is able to reduce wait times by over 3x and improve fidelity by over 40% on specific usecases, when compared to traditional job schedulers.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1051/epjconf/202024507046
