Author name cluster

Maria Christakis

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

IJCAI Conference 2025 Conference Paper

Lazy Testing of Machine-Learning Models

Anastasia Isychev
Valentin Wüstholz
Maria Christakis

Checking the reliability of machine-learning models is a crucial, but challenging task. Nomos is an existing, automated framework for testing general, user-provided functional properties of models, including so-called hyperproperties expressed over more than one model execution. Nomos aims to find model inputs that expose ``bugs'', that is, property violations. However, performing thousands of model invocations during testing is costly both in terms of time and money (for metered APIs, such as OpenAI's). We present LaZ (pronounced ``lazy''), an extension of Nomos that automatically minimizes the number of model invocations to boost the test throughput and thereby find bugs more efficiently. During test execution, LaZ automatically identifies redundant invocations---invocations where the model output does not affect the final test outcome---and skips them, much like lazy evaluation in certain programming languages. This optimization enables a second one that dynamically reorders model invocations to skip the more expensive ones. As a result, LaZ finds the same number of bugs as Nomos, but does so median 33% and up to 60% faster.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Automatically Testing Functional Properties of Code Translation Models

Hasan Ferit Eniser
Valentin Wüstholz
Maria Christakis

Large language models are becoming increasingly practical for translating code across programming languages, a process known as transpiling. Even though automated transpilation significantly boosts developer productivity, a key concern is whether the generated code is correct. Existing work initially used manually crafted test suites to test the translations of a small corpus of programs; these test suites were later automated. In contrast, we devise the first approach for automated, functional, property-based testing of code translation models. Our general, user-provided specifications about the transpiled code capture a range of properties, from purely syntactic to purely semantic ones. As shown by our experiments, this approach is very effective in detecting property violations in popular code translation models, and therefore, in evaluating model quality with respect to given properties. We also go a step further and explore the usage scenario where a user simply aims to obtain a correct translation of some code with respect to certain properties without necessarily being concerned about the overall quality of the model. To this purpose, we develop the first property-guided search procedure for code translation models, where a model is repeatedly queried with slightly different parameters to produce alternative and potentially more correct translations. Our results show that this search procedure helps to obtain significantly better code translations.

PDF Details DOI

ICAPS Conference 2024 Conference Paper

New Fuzzing Biases for Action Policy Testing

Jan Eisenhut
Xandra Schuler
Daniel Fiser
Daniel Höller
Maria Christakis
Jörg Hoffmann 0001

Testing was recently proposed as a method to gain trust in learned action policies in classical planning. Test cases in this setting are states generated by a fuzzing process that performs random walks from the initial state. A fuzzing bias attempts to bias these random walks towards policy bugs, that is, states where the policy performs sub-optimally. Prior work explored a simple fuzzing bias based on policy-trace cost. Here, we investigate this topic more deeply. We introduce three new fuzzing biases based on analyses of policy-trace shape, estimating whether a trace is close to looping back on itself, whether it contains detours, and whether its goal-distance surface does not smoothly decline. Our experiments with two kinds of neural action policies show that these new biases improve bug-finding capabilities in many cases.

Details

ICAPS Conference 2023 Conference Paper

Automatic Metamorphic Test Oracles for Action-Policy Testing

Jan Eisenhut
Álvaro Torralba
Maria Christakis
Jörg Hoffmann 0001

Testing is a promising way to gain trust in learned action policies π. Prior work on action-policy testing in AI planning formalized bugs as states t where π is sub-optimal with respect to a given testing objective. Deciding whether or not t is a bug is as hard as (optimal) planning itself. How can we design test oracles able to recognize some states t to be bugs efficiently? Recent work introduced metamorphic oracles which compare policy behavior on state pairs (s, t) where t is easier to solve; if π performs worse on t than on s, we know that t is a bug. Here, we show how to automatically design such oracles in classical planning, based on simulation relations between states. We introduce two oracle families of this kind: first, morphing query states t to obtain suitable s; second, maintaining and comparing upper bounds on h* across the states encountered during testing. Our experiments on ASNet policies show that these oracles can find bugs much more quickly than the existing alternatives, which are search-based; and that the combination of our oracles with search-based ones almost consistently dominates all other oracles.

Details

IJCAI Conference 2023 Conference Paper

Specifying and Testing k-Safety Properties for Machine-Learning Models

Maria Christakis
Hasan Ferit Eniser
Jörg Hoffmann
Adish Singla
Valentin Wüstholz

Machine-learning models are becoming increasingly prevalent in our lives, for instance assisting in image-classification or decision-making tasks. Consequently, the reliability of these models is of critical importance and has resulted in the development of numerous approaches for validating and verifying their robustness and fairness. However, beyond such specific properties, it is challenging to specify, let alone check, general functional-correctness expectations from models. In this paper, we take inspiration from specifications used in formal methods, expressing functional-correctness properties by reasoning about k different executions---so-called k-safety properties. Considering a credit-screening model of a bank, the expected property that "if a person is denied a loan and their income decreases, they should still be denied the loan" is a 2-safety property. Here, we show the wide applicability of k-safety properties for machine-learning models and present the first specification language for expressing them. We also operationalize the language in a framework for automatically validating such properties using metamorphic testing. Our experiments show that our framework is effective in identifying property violations, and that detected bugs could be used to train better models.

PDF Details DOI

ICAPS Conference 2022 Conference Paper

Debugging a Policy: Automatic Action-Policy Testing in AI Planning

Marcel Steinmetz
Daniel Fiser
Hasan Ferit Eniser
Patrick Ferber
Timo P. Gros
Philippe Heim
Daniel Höller
Xandra Schuler

Testing is a promising way to gain trust in neural action policies π. Previous work on policy testing in sequential decision making targeted environment behavior leading to failure conditions. But if the failure is unavoidable given that behavior, then π is not actually to blame. For a situation to qualify as a "bug" in π, there must be an alternative policy π' that does better. We introduce a generic policy testing framework based on that intuition. This raises the bug confirmation problem, deciding whether or not a state is a bug. We analyze the use of optimistic and pessimistic bounds for the design of test oracles approximating that problem. We contribute an implementation of our framework in classical planning, experimenting with several test oracles and with random-walk methods generating test states biased to poor policy performance and/or state novelty. We evaluate these techniques on policies π learned with ASNets. We find that they are able to effectively identify bugs in these π, and that our random-walk biases improve over uninformed baselines.

Details

NeurIPS Conference 2020 Conference Paper

Synthesizing Tasks for Block-based Programming

Umair Ahmed
Maria Christakis
Aleksandr Efremov
Nigel Fernandez
Ahana Ghosh
Abhik Roychoudhury
Adish Singla

Block-based visual programming environments play a critical role in introducing computing concepts to K-12 students. One of the key pedagogical challenges in these environments is in designing new practice tasks for a student that match a desired level of difficulty and exercise specific programming concepts. In this paper, we formalize the problem of synthesizing visual programming tasks. In particular, given a reference visual task $\task^{in}$ and its solution code $\code^{in}$, we propose a novel methodology to automatically generate a set $\{(\task^{out}, \code^{out})\}$ of new tasks along with solution codes such that tasks $\task^{in}$ and $\task^{out}$ are conceptually similar but visually dissimilar. Our methodology is based on the realization that the mapping from the space of visual tasks to their solution codes is highly discontinuous; hence, directly mutating reference task $\task^{in}$ to generate new tasks is futile. Our task synthesis algorithm operates by first mutating code $\code^{in}$ to obtain a set of codes $\{\code^{out}\}$. Then, the algorithm performs symbolic execution over a code $\code^{out}$ to obtain a visual task $\task^{out}$; this step uses the Monte Carlo Tree Search (MCTS) procedure to guide the search in the symbolic tree. We demonstrate the effectiveness of our algorithm through an extensive empirical evaluation and user study on reference tasks taken from the Hour of Code: Classic Maze challenge by Code. org and the Intro to Programming with Karel course by CodeHS. com.

PDF Details