Ease.ml/snoopy in action

Renggli, Cédric; Rimanic, Luka; Kolar, Luka; Wu, Wentao; Zhang, Ce

doi:10.14778/3415478.3415488

Cited by 8 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speci cally, we use Cherubin's codebase [9] to experiment with the Tamaraw and CS-BuFLO defenses, as well as the WFES estimator; Gong et al 's repository [26] to experiment with the FRONT and WTF-PAD defenses; and Rahman et al 's re-implementation of WeFDE [62]. We also implemented the kNN-based BER estimator proposed by Renggli et al [66].…”

Section: Methodsmentioning

confidence: 99%

“…DeepSE-WF (this work) Learned DL BER & MI using nite datasets is an extensively researched problem in the eld of machine learning [5,13,17,21,22,60,66,72]. Inspired by Cover and Hart [13], Cherubin reduces the WF problem to a classi cation task and leverages the error of the Nearest Neighbor classi er as a proxy to estimate the lower bound for the error of any potential classi er used on prede ned features.…”

Section: Estimator Features Metricmentioning

confidence: 99%

“…Guided by the reasoning in observation (2) and the fact that the sum of nite-sample bias and transformation bias are positive and typically strictly larger than the tightness of the lower bound estimate, it is natural that even without having knowledge of the additional induced biases the NN-based estimators can only bene t from deterministic feature transformations in the nite-sample case. A natural consequence of this is that one can simply achieve a better estimate of the BER by not only inspecting a single representation, but rather try many di erent transformations and report the minimal achieved BER [66]. Note that a theoretical counterpart for NN-based MI estimators (e.g., negative nite-sample bias) is missing.…”

Section: Theoretical Reasoningmentioning

confidence: 99%

See 2 more Smart Citations

DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses

Veicht

Renggli

Barradas

2023

PoPETs

View full text Add to dashboard Cite

Website fingerprinting (WF) attacks, usually conducted with the help of a machine learning-based classifier, enable a network eavesdropper to pinpoint which website a user is accessing through the inspection of traffic patterns. These attacks have been shown to succeed even when users browse the Internet through encrypted tunnels, e.g., through Tor or VPNs. To assess the security of new defenses against WF attacks, recent works have proposed feature-dependent theoretical frameworks that estimate the Bayes error of an adversary's features set or the mutual information leaked by manually-crafted features. Unfortunately, as WF attacks increasingly rely on deep learning and latent feature spaces, our experiments show that security estimations based on simpler (and less informative) manually-crafted features can no longer be trusted to assess the potential success of a WF adversary in defeating such defenses. In this work, we propose DeepSE-WF, a novel WF security estimation framework that leverages specialized kNN-based estimators to produce Bayes error and mutual information estimates from learned latent feature spaces, thus bridging the gap between current WF attacks and security estimation methods. Our evaluation reveals that DeepSE-WF produces tighter security estimates than previous frameworks, reducing the required computational resources to output security estimations by one order of magnitude.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Estimator Features Metricmentioning

confidence: 99%

Section: Theoretical Reasoningmentioning

confidence: 99%

See 1 more Smart Citation

DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses

Veicht

Renggli

Barradas

2023

PoPETs

View full text Add to dashboard Cite

show abstract

“…The serving can be provided, e.g., via a REST API. As a foundational infrastructure layer, a scalable and distributed model serving infrastructure is recommended [23], [27], [33], [37], [39], [46] Additionally, monitoring of the ML infrastructure, CI/CD, and orchestration are required [7], [23], [24], [28], [32], [33], [50]…”

Section: C3 Workflow Orchestration Component (P2 P3 P6)mentioning

confidence: 99%

Machine Learning Operations (MLOps): Overview, Definition, and Architecture

2023

View full text Add to dashboard Cite

The final goal of all industrial machine learning (ML) projects is to develop ML products and rapidly bring them into production. However, it is highly challenging to automate and operationalize ML products and thus many ML endeavors fail to deliver on their expectations. The paradigm of Machine Learning Operations (MLOps) addresses this issue. MLOps includes several aspects, such as best practices, sets of concepts, and development culture. However, MLOps is still a vague term and its consequences for researchers and professionals are ambiguous. To address this gap, we conduct mixed-method research, including a literature review, a tool review, and expert interviews. As a result of these investigations, we contribute to the body of knowledge by providing an aggregated overview of the necessary principles, components, and roles, as well as the associated architecture and workflows. Furthermore, we provide a comprehensive definition of MLOps and highlight open challenges in the field. Finally, this work provides guidance for ML researchers and practitioners who want to automate and operate their ML products with a designated set of technologies.

show abstract

“…, 2022; Mäkinen et al. , 2021; Renggli et al. , 2021) and organizational research on AI/ML use and management (Berente et al.…”

Section: Introductionmentioning

confidence: 99%

Riding a bicycle while building its wheels: the process of machine learning-based capability development and IT-business alignment practices

Mucha,

Ma,

Abhari

2023

INTR

View full text Add to dashboard Cite

PurposeRecent advancements in Artificial Intelligence (AI) and, at its core, Machine Learning (ML) offer opportunities for organizations to develop new or enhance existing capabilities. Despite the endless possibilities, organizations face operational challenges in harvesting the value of ML-based capabilities (MLbC), and current research has yet to explicate these challenges and theorize their remedies. To bridge the gap, this study explored the current practices to propose a systematic way of orchestrating MLbC development, which is an extension of ongoing digitalization of organizations.Design/methodology/approachData were collected from Finland's Artificial Intelligence Accelerator (FAIA) and complemented by follow-up interviews with experts outside FAIA in Europe, China and the United States over four years. Data were analyzed through open coding, thematic analysis and cross-comparison to develop a comprehensive understanding of the MLbC development process.FindingsThe analysis identified the main components of MLbC development, its three phases (development, release and operation) and two major MLbC development challenges: Temporal Complexity and Context Sensitivity. The study then introduced Fostering Temporal Congruence and Cultivating Organizational Meta-learning as strategic practices addressing these challenges.Originality/valueThis study offers a better theoretical explanation for the MLbC development process beyond MLOps (Machine Learning Operations) and its hindrances. It also proposes a practical way to align ML-based applications with business needs while accounting for their structural limitations. Beyond the MLbC context, this study offers a strategic framework that can be adapted for different cases of digital transformation that include automation and augmentation of work.

show abstract

Ease.ml/snoopy in action

Cited by 8 publications

References 16 publications

DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses

DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses

Machine Learning Operations (MLOps): Overview, Definition, and Architecture

Riding a bicycle while building its wheels: the process of machine learning-based capability development and IT-business alignment practices

Contact Info

Product

Resources

About