1 code implementation • 7 Sep 2023 • Hasan Ferit Eniser, Valentin Wüstholz, Maria Christakis
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.
1 code implementation • 27 May 2023 • Alperen Tercan, Ahana Ghosh, Hasan Ferit Eniser, Maria Christakis, Adish Singla
We propose a novel synthesis algorithm that generates a progression of subtasks that are high-quality, well-spaced in terms of their complexity, and solving this progression leads to solving the reference task.
1 code implementation • 13 Jun 2022 • Maria Christakis, Hasan Ferit Eniser, Jörg Hoffmann, Adish Singla, Valentin Wüstholz
Here, we show the wide applicability of $k$-safety properties for machine-learning models and present the first specification language for expressing them.
no code implementations • 9 Feb 2020 • Simos Gerasimou, Hasan Ferit Eniser, Alper Sen, Alper Cakan
Deep Learning (DL) systems are key enablers for engineering intelligent applications due to their ability to solve complex tasks such as image recognition and machine translation.
no code implementations • 7 Feb 2020 • Hasan Ferit Eniser, Maria Christakis, Valentin Wüstholz
In recent years, neural networks have become the default choice for image classification and many other learning tasks, even though they are vulnerable to so-called adversarial attacks.
1 code implementation • 24 Nov 2019 • Samet Demir, Hasan Ferit Eniser, Alper Sen
Among those, CGF aims to produce new test inputs by fuzzing existing ones to achieve high coverage on a test adequacy criterion (i. e. coverage criterion).
no code implementations • 15 Feb 2019 • Hasan Ferit Eniser, Simos Gerasimou, Alper Sen
Deep Neural Networks (DNNs) are increasingly deployed in safety-critical applications including autonomous vehicles and medical diagnostics.