LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Zurück zur letzten Suche Suchhistorie
Erweiterte Suche

Ihre letzten Suchen

  1. AU="Grana, Justin"
  2. AU="Thiel, Uwe"
  3. AU="Zhao, Jinlong"
  4. AU="Paresce, Erberto"
  5. AU=Theerthakarai R
  6. AU="Glenson S. France"
  7. AU=Cai Yi
  8. AU="Elbasiouny, Sherif M"
  9. AU=Bhandarkar Deepraj S
  10. AU="Stefano Masiero"
  11. AU=Zhang Jin-Ying
  12. AU="Cho, Yun-Ho"
  13. AU=Chatr-aryamontri Andrew
  14. AU="Thompson, Kristin"
  15. AU="Horiguchi, Kumiko"
  16. AU="Wagner, Franz F"
  17. AU="Mishra, Vandana"
  18. AU=Zucker Irving H
  19. AU=Dang Vinh T
  20. AU="Andrea Benedetti"
  21. AU="Xu, Jiyu"
  22. AU="Dawson, Holli E"
  23. AU="Dominy, Katherine M"
  24. AU="Maunik Chapala"
  25. AU="Luksic, Ivica"
  26. AU="Mastronardi, Luciano"
  27. AU="Md Farijul Islam"
  28. AU="Quansah, Gabriel W"
  29. AU="Keane, Stephen"
  30. AU="Marsela, Enklajd"
  31. AU="Tate, Amanda W"
  32. AU="Solodov, E P"
  33. AU="Cheng-Fang Yen"

Suchergebnis

Treffer 1 - 7 von insgesamt 7

Suchoptionen

  1. Buch ; Online: Perturbing Inputs to Prevent Model Stealing

    Grana, Justin

    2020  

    Abstract: We show how perturbing inputs to machine learning services (ML-service) deployed in the cloud can protect against model stealing attacks. In our formulation, there is an ML-service that receives inputs from users and returns the output of the model. ... ...

    Abstract We show how perturbing inputs to machine learning services (ML-service) deployed in the cloud can protect against model stealing attacks. In our formulation, there is an ML-service that receives inputs from users and returns the output of the model. There is an attacker that is interested in learning the parameters of the ML-service. We use the linear and logistic regression models to illustrate how strategically adding noise to the inputs fundamentally alters the attacker's estimation problem. We show that even with infinite samples, the attacker would not be able to recover the true model parameters. We focus on characterizing the trade-off between the error in the attacker's estimate of the parameters with the error in the ML-service's output.
    Schlagwörter Computer Science - Cryptography and Security ; Computer Science - Machine Learning
    Erscheinungsdatum 2020-05-12
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  2. Buch ; Online: Uncertainty Quantification for Local Model Explanations Without Model Access

    Ahn, Surin / Grana, Justin / Tamene, Yafet / Holsheimer, Kristian

    2023  

    Abstract: We present a model-agnostic algorithm for generating post-hoc explanations and uncertainty intervals for a machine learning model when only a static sample of inputs and outputs from the model is available, rather than direct access to the model itself. ... ...

    Abstract We present a model-agnostic algorithm for generating post-hoc explanations and uncertainty intervals for a machine learning model when only a static sample of inputs and outputs from the model is available, rather than direct access to the model itself. This situation may arise when model evaluations are expensive; when privacy, security and bandwidth constraints are imposed; or when there is a need for real-time, on-device explanations. Our algorithm uses a bootstrapping approach to quantify the uncertainty that inevitably arises when generating explanations from a finite sample of model queries. Through a simulation study, we show that the uncertainty intervals generated by our algorithm exhibit a favorable trade-off between interval width and coverage probability compared to the naive confidence intervals from classical regression analysis as well as current Bayesian approaches for quantifying explanation uncertainty. We further demonstrate the capabilities of our method by applying it to black-box models, including a deep neural network, trained on three real-world datasets.
    Schlagwörter Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Statistics - Methodology
    Thema/Rubrik (Code) 310
    Erscheinungsdatum 2023-01-13
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  3. Artikel ; Online: How Much Would You Pay to Change a Game before Playing It?

    Wolpert, David / Grana, Justin

    Entropy (Basel, Switzerland)

    2019  Band 21, Heft 7

    Abstract: Envelope theorems provide a differential framework for determining how much a rational decision maker (DM) is willing to pay to alter the parameters of a strategic scenario. We generalize this framework to the case of a boundedly rational DM and ... ...

    Abstract Envelope theorems provide a differential framework for determining how much a rational decision maker (DM) is willing to pay to alter the parameters of a strategic scenario. We generalize this framework to the case of a boundedly rational DM and arbitrary solution concepts. We focus on comparing and contrasting the case where DM's decision to pay to change the parameters is observed by all other players against the case where DM's decision is private information. We decompose DM's willingness to pay a given amount into a sum of three factors: (1) the direct effect a parameter change would have on DM's payoffs in the future strategic scenario, holding strategies of all players constant; (2) the effect due to DM changing its strategy as they react to a change in the game parameters, with the strategies of the
    Sprache Englisch
    Erscheinungsdatum 2019-07-13
    Erscheinungsland Switzerland
    Dokumenttyp Journal Article
    ZDB-ID 2014734-X
    ISSN 1099-4300 ; 1099-4300
    ISSN (online) 1099-4300
    ISSN 1099-4300
    DOI 10.3390/e21070686
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

  4. Buch ; Online: Content Filtering with Inattentive Information Consumers

    Ball, Ian / Bono, James / Grana, Justin / Immorlica, Nicole / Lucier, Brendan / Slivkins, Alex

    2022  

    Abstract: We develop and analyze a model of content filtering where the content consumers incur deliberation costs when deciding the veracity of the content. Examples of such a scenario include censoring misinformation, information security (spam and phish ... ...

    Abstract We develop and analyze a model of content filtering where the content consumers incur deliberation costs when deciding the veracity of the content. Examples of such a scenario include censoring misinformation, information security (spam and phish filtering, for example) and recommender systems. With an exogenous attack probability, we show that increasing the quality of the filter is typically weakly Pareto improving though may sometimes have no impact on equilibrium outcomes and payoffs. Furthermore, when the filter does not internalize the consumer's deliberation costs, the filter's lack of commitment power may render a low-fidelity filter useless and lead to inefficient outcomes. Consequently, improvements to a moderately effective filter will have no impact on equilibrium payoffs until the filter is sufficiently accurate. With an endogenous attacker, improvements to filter quality may lead to strictly lower equilibrium payoffs since the content consumer increases its trust in the filter and thus incentivizes the attacker to increase its attack propensity.
    Schlagwörter Economics - Theoretical Economics
    Thema/Rubrik (Code) 303
    Erscheinungsdatum 2022-05-27
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  5. Buch ; Online: Policy-focused Agent-based Modeling using RL Behavioral Models

    Osoba, Osonde A. / Vardavas, Raffaele / Grana, Justin / Zutshi, Rushil / Jaycocks, Amber

    2020  

    Abstract: Agent-based Models (ABMs) are valuable tools for policy analysis. ABMs help analysts explore the emergent consequences of policy interventions in multi-agent decision-making settings. But the validity of inferences drawn from ABM explorations depends on ... ...

    Abstract Agent-based Models (ABMs) are valuable tools for policy analysis. ABMs help analysts explore the emergent consequences of policy interventions in multi-agent decision-making settings. But the validity of inferences drawn from ABM explorations depends on the quality of the ABM agents' behavioral models. Standard specifications of agent behavioral models rely either on heuristic decision-making rules or on regressions trained on past data. Both prior specification modes have limitations. This paper examines the value of reinforcement learning (RL) models as adaptive, high-performing, and behaviorally-valid models of agent decision-making in ABMs. We test the hypothesis that RL agents are effective as utility-maximizing agents in policy ABMs. We also address the problem of adapting RL algorithms to handle multi-agency in games by adapting and extending methods from recent literature. We evaluate the performance of such RL-based ABM agents via experiments on two policy-relevant ABMs: a minority game ABM, and an ABM of Influenza Transmission. We run some analytic experiments on our AI-equipped ABMs e.g. explorations of the effects of behavioral heterogeneity in a population and the emergence of synchronization in a population. The experiments show that RL behavioral models are effective at producing reward-seeking or reward-maximizing behaviors in ABM agents. Furthermore, RL behavioral models can learn to outperform the default adaptive behavioral models in the two ABMs examined.

    Comment: This is a more detailed version of a paper ("Modeling Agent Behaviors for Policy Analysis via Reinforcement Learning") accepted to appear in IEEE ICMLA 2020. This also corrects an error in Fig. 7 of the original arXiv submission. Fig. 7 now specifies the right ABM architecture ("flu" instead of "tax")
    Schlagwörter Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Computer Science - Multiagent Systems
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2020-06-09
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  6. Buch ; Online: A Likelihood Ratio Detector for Identifying Within-Perimeter Computer Network Attacks

    Grana, Justin / Wolpert, David / Neil, Joshua / Xie, Dongping / Bhattacharya, Tanmoy / Bent, Russel

    2016  

    Abstract: The rapid detection of attackers within firewalls of enterprise computer net- works is of paramount importance. Anomaly detectors address this problem by quantifying deviations from baseline statistical models of normal network behav- ior and signaling ... ...

    Abstract The rapid detection of attackers within firewalls of enterprise computer net- works is of paramount importance. Anomaly detectors address this problem by quantifying deviations from baseline statistical models of normal network behav- ior and signaling an intrusion when the observed data deviates significantly from the baseline model. However, many anomaly detectors do not take into account plausible attacker behavior. As a result, anomaly detectors are prone to a large number of false positives due to unusual but benign activity. This paper first in- troduces a stochastic model of attacker behavior which is motivated by real world attacker traversal. Then, we develop a likelihood ratio detector that compares the probability of observed network behavior under normal conditions against the case when an attacker has possibly compromised a subset of hosts within the network. Since the likelihood ratio detector requires integrating over the time each host be- comes compromised, we illustrate how to use Monte Carlo methods to compute the requisite integral. We then present Receiver Operating Characteristic (ROC) curves for various network parameterizations that show for any rate of true posi- tives, the rate of false positives for the likelihood ratio detector is no higher than that of a simple anomaly detector and is often lower. We conclude by demon- strating the superiority of the proposed likelihood ratio detector when the network topologies and parameterizations are extracted from real-world networks.
    Schlagwörter Computer Science - Cryptography and Security
    Thema/Rubrik (Code) 519 ; 303
    Erscheinungsdatum 2016-09-01
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  7. Buch ; Online: Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes

    Menda, Kunal / Chen, Yi-Chun / Grana, Justin / Bono, James W. / Tracey, Brendan D. / Kochenderfer, Mykel J. / Wolpert, David

    2017  

    Abstract: The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems. Since macro-actions last for stochastic durations, ... ...

    Abstract The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems. Since macro-actions last for stochastic durations, multiple agents executing decentralized policies in cooperative environments must act asynchronously. We present an algorithm that modifies generalized advantage estimation for temporally extended actions, allowing a state-of-the-art policy optimization algorithm to optimize policies in Dec-POMDPs in which agents act asynchronously. We show that our algorithm is capable of learning optimal policies in two cooperative domains, one involving real-time bus holding control and one involving wildfire fighting with unmanned aircraft. Our algorithm works by framing problems as "event-driven decision processes," which are scenarios in which the sequence and timing of actions and events are random and governed by an underlying stochastic process. In addition to optimizing policies with continuous state and action spaces, our algorithm also facilitates the use of event-driven simulators, which do not require time to be discretized into time-steps. We demonstrate the benefit of using event-driven simulation in the context of multiple agents taking asynchronous actions. We show that fixed time-step simulation risks obfuscating the sequence in which closely separated events occur, adversely affecting the policies learned. In addition, we show that arbitrarily shrinking the time-step scales poorly with the number of agents.

    Comment: Published in IEEE Transactions on Intelligent Transportation Systems (Volume: 20, Issue: 4, April 2019). https://ieeexplore.ieee.org/document/8419722
    Schlagwörter Computer Science - Artificial Intelligence ; Computer Science - Multiagent Systems
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2017-09-19
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang