检索结果-内蒙古大学图书馆

Sensitive samples revisited: Detecting neural network attacks using constraint solvers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Docena, Amel Nestor Wahl, Thomas Pearce, Trevor Fei, Yunsi Khoury College of Computer Sciences Northeastern University Boston United States

Neural Networks are used today in numerous security- and safety-relevant domains and are, as such, a popular target of attacks that subvert their classification capabilities, by manipulating the network parameters. Prior work has introduced sensitive samples—inputs highly sensitive to parameter changes—to detect such manipulations, and proposed a gradient ascent-based approach to compute them. In this paper we offer an alternative, using symbolic constraint solvers. We model the network and a formal specification of a sensitive sample in the language of the solver and ask for a solution. This approach supports a rich class of queries, corresponding, for instance, to the presence of certain types of attacks. Unlike earlier techniques, our approach does not depend on convex search domains, or on the suitability of a starting point for the search. We address the performance limitations of constraint solvers by partitioning the search space for the solver, and exploring the partitions according to a balanced schedule that still retains completeness of the search. We demonstrate the impact of the use of solvers in terms of functionality and search efficiency, using a case study for the detection of Trojan attacks on Neural Networks. © 2021, CC BY.

关键词： logic programming

Reactive answer set programming

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Broda, Krysia Sadri, Fariba Butler, Stephen Imperial College London

logic Production System (LPS) is a logic-based framework for modelling reactive behaviour. Based on abductive logic programming, it combines reactive rules with logic programs, a database and a causal theory that specifies transitions between the states of the database. This paper proposes a systematic mapping of the Kernel of this framework (called KELPS) into an answer set program (ASP). For this purpose a new variant of KELPS with finite models, called n-distance KELPS, is introduced. A formal definition of the mapping from this n-distance KELPS to ASP is given and proven sound and complete. The Answer Set programming paradigm allows to capture additional behaviours to the basic reactivity of KELPS, in particular proactive, preemptive and prospective behaviours. These are all discussed and illustrated with examples. Then a hybrid framework is proposed that integrates KELPS and ASP, allowing to combine the strengths of both paradigms. Copyright © 2021, The Authors. All rights reserved.

关键词： logic programming

Refining the semantics of epistemic specifications

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Su, Ezgi Iraz Sinop University Department of Computer Engineering Sinop Turkey

Answer set programming (ASP) is a problem-solving approach, which has been strongly supported both scientifically and technologically by several solvers, ongoing active research, and implementations in many different fields. However, although researchers acknowledged long ago the necessity of epistemic operators in the language of ASP for better introspective reasoning, this research venue did not attract much attention until recently. Moreover, the existing epistemic extensions of ASP in the literature are not widely approved either, due to the fact that some propose unintended results even for some simple acyclic epistemic programs, new unexpected results may possibly be found, and more importantly, researchers have different reasonings for some critical programs. To that end, Cabalar et al. have recently identified some structural properties of epistemic programs to formally support a possible semantics proposal of such programs and standardise their results. Nonetheless, the soundness of these properties is still under debate, and they are not widely accepted either by the ASP community. Thus, it seems that there is still time to really understand the paradigm, have a mature formalism, and determine the principles providing formal justification of their understandable models. In this paper, we mainly focus on the existing semantics approaches, the criteria that a satisfactory semantics is supposed to satisfy, and the ways to improve them. We also extend some well-known propositions of here-and-there logic (HT) into epistemic HT so as to reveal the real behaviour of programs. Finally, we propose a slightly novel semantics for epistemic ASP, which can be considered as a reflexive extension of Cabalar et al.'s recent formalism called autoepistemic ASP. © 2021, CC BY.

关键词： logic programming

Forgetting in Answer Set programming – A Survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gonçalves, Ricardo Knorr, Matthias Leite, João NOVA LINCS Departamento de Informática Faculdade de Ciências e Tecnologia Universidade Nova de Lisboa Portugal

Forgetting – or variable elimination – is an operation that allows the removal, from a knowledge base, of middle variables no longer deemed relevant. In recent years, many different approaches for forgetting in Answer Set programming have been proposed, in the form of specific operators, or classes of such operators, commonly following different principles and obeying different properties. Each such approach was developed to address some particular view on forgetting, aimed at obeying a specific set of properties deemed desirable in such view, but a comprehensive and uniform overview of all the existing operators and properties is missing. In this paper, we thoroughly examine existing properties and (classes of) operators for forgetting in Answer Set programming, drawing a complete picture of the landscape of these classes of forgetting operators, which includes many novel results on relations between properties and operators, including considerations on concrete operators to compute results of forgetting and computational complexity. Our goal is to provide guidance to help users in choosing the operator most adequate for their application requirements. © 2021, CC BY-NC-SA.

关键词： logic programming

Regular path clauses and their application in solving loops

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kafle, Bishoksan Gallagher, John P. Hermenegildo, Manuel V. Klemen, Maximiliano López-García, Pedro Morales, José F. IMDEA Software Institute Spain Roskilde University Denmark U. Politécnica de Madrid Spain

A well-established approach to reasoning about loops during program analysis is to capture the effect of a loop by extracting recurrences from the loop;these express relationships between the values of variables, or program properties such as cost, on successive loop iterations. Recurrence solvers are capable of computing closed forms for some recurrences, thus deriving precise relationships capturing the complete loop execution. However, many recurrences extracted from loops cannot be solved, due to their having multiple recursive cases or multiple arguments. In the literature, several techniques for approximating the solution of unsolvable recurrences have been proposed. The approach presented in this paper is to define transformations based on regular path expressions and loop counters that (i) transform multi-path loops to single-path loops, giving rise to recurrences with a single recursive case, and (ii) transform multi-argument recurrences to single-argument recurrences, thus enabling the use of recurrence solvers on the transformed recurrences. Using this approach, precise solutions can sometimes be obtained that are not obtained by approximation methods. © 2021, CC BY.

关键词： logic programming

How to split a logic program

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ben-Eliyahu-Zohary, Rachel Department of Software Engineering JCE-Azrieli College of Engineering Jerusalem Israel

Answer Set programming (ASP) is a successful method for solving a range of real-world applications. Despite the availability of fast ASP solvers, computing answer sets demands a very large computational power, since the problem tackled is in the second level of the polynomial hierarchy. A speed-up in answer set computation may be attained, if the program can be split into two disjoint parts, bottom and top. Thus, the bottom part is evaluated independently of the top part, and the results of the bottom part evaluation are used to simplify the top part. Lifschitz and Turner have introduced the concept of a splitting set, i.e., a set of atoms that defines the splitting. In this paper, We show that the problem of computing a splitting set with some desirable properties can be reduced to a classic Search Problem and solved in polynomial time. This allows us to conduct experiments on the size of the splitting set in various programs and lead to an interesting discoery of a source of complication in stable model computation. We also show that for Head-Cycle-Free programs, the definition of splitting sets can be adjusted to allow splitting of a broader class of programs. © 2021, CC BY.

关键词： logic programming

SLD-resolution without occur-check, an example

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Drabent, Wlodzimierz Institute of Computer Science Polish Academy of Sciences IDA Linköping University Sweden

We prove that the occur-check is not needed for a certain definite clause logic program, independently from the selection rule. First we prove that the program is occur-check free. Then we consider a more general class of queries, under which the program is not occur-check free;however we show that it will be correctly executed under Prolog without occur-check. The main result of this report states that the occur-check may be skipped for the cases in which a single run of a standard nondeterministic unification algorithm does not fail due to the occur-check. The usual approaches are based on the notion of NSTO (not subject to occur-check), which considers all the runs. To formulate the result, it was necessary to introduce an abstraction of a "unification" algorithm without the *** Codes 68N17 03B10 Copyright © 2021, The Authors. All rights reserved.

关键词： logic programming

An empirical study of partial deduction for MINIKANREN

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Verbitskaia, Ekaterina Berezun, Daniil Boulytchev, Dmitry JetBrains Research Saint Petersburg Russia Saint Petersburg State University JetBrains Research Saint Petersburg Russia

We study conjunctive partial deduction, an advanced specialization technique aimed at improving the performance of logic programs, in the context of relational programming language MINIKANREN. We identify a number of issues, caused by MINIKANREN peculiarities, and describe a novel approach to specialization based on partial deduction and supercompilation. The results of the evaluation demonstrate successful specialization of relational interpreters. Although the project is at an early stage, we consider it as the first step towards an efficient optimization framework for MINIKANREN. © 2021, CC BY.

关键词： logic programming

Rushing and Strolling among Answer Sets – Navigation Made Easy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fichte, Johannes Klaus Gaggl, Sarah Alice Rusovac, Dominik TU Wien Austria TU Dresden Germany

Answer set programming (ASP) is a popular declarative programming paradigm with a wide range of applications in artificial intelligence. Oftentimes, when modeling an AI problem with ASP, and in particular when we are interested beyond simple search for optimal solutions, an actual solution, differences between solutions, or number of solutions of the ASP program matter. For example, when a user aims to identify a specific answer set according to her needs, or requires the total number of diverging solutions to comprehend probabilistic applications such as reasoning in medical domains. Then, there are only certain problem specific and handcrafted encoding techniques available to navigate the solution space of ASP programs, which is oftentimes not enough. In this paper, we propose a formal and general framework for interactive navigation towards desired subsets of answer sets analogous to faceted browsing. Our approach enables the user to explore the solution space by consciously zooming in or out of sub-spaces of solutions at a certain configurable pace. We illustrate that weighted faceted navigation is computationally hard. Finally, we provide an implementation of our approach that demonstrates the feasibility of our framework for incomprehensible solution spaces. Copyright © 2021, The Authors. All rights reserved.

关键词： logic programming