{"id":3643,"date":"2022-12-17T21:13:40","date_gmt":"2022-12-17T21:13:40","guid":{"rendered":"http:\/\/cad4security.org\/?page_id=3643"},"modified":"2022-12-18T17:39:38","modified_gmt":"2022-12-18T17:39:38","slug":"tensorfi-2-a-fault-injector-for-tensorflow-2-applications","status":"publish","type":"page","link":"http:\/\/cad4security.org\/index.php\/cad-tools\/fault-injection-analysis\/tensorfi-2-a-fault-injector-for-tensorflow-2-applications\/","title":{"rendered":"TensorFI 2: A fault injector for TensorFlow 2 applications"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">Tool Name<\/h2>\n\n\n\n<p>TensorFI 2: A fault injector for TensorFlow 2 applications<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Description<\/strong><\/h2>\n\n\n\n<p>TensorFI 2 is a fault injector for TensorFlow 2 applications written in Python 3. We make use of the Keras Model APIs to inject static faults in the layer states and dynamic faults in the layer outputs. Similar to\u00a0<a href=\"https:\/\/github.com\/DependableSystemsLab\/TensorFI\">TensorFI 1<\/a>, TensorFI 2 supports both hardware and software faults with different injection modes. The fault injector is easily configurable with YAML.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>More Info<\/strong><\/h2>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a class=\"wp-block-button__link button\" href=\"\" target=\"_blank\" rel=\"noreferrer noopener\">Tool link<\/a><\/div>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Publications\/References<\/strong><\/h2>\n\n\n\n<p>Z. Chen, N. Narayanan, B. Fang, G. Li, K. Pattabiraman and N. DeBardeleben, &#8220;TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications,&#8221;\u00a0<em>2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE)<\/em>, 2020, pp. 426-435, doi: 10.1109\/ISSRE5003.2020.00047. <a rel=\"noreferrer noopener\" href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/9251063\" target=\"_blank\">https:\/\/ieeexplore.ieee.org\/abstract\/document\/9251063<\/a><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Contacts<\/strong><\/h2>\n\n\n","protected":false},"excerpt":{"rendered":"<p>Tool Name TensorFI 2: A fault injector for TensorFlow 2 applications Description TensorFI 2 is a fault injector for TensorFlow 2 applications written in Python 3. We make use of the Keras Model APIs to inject static faults in the layer states and dynamic faults in the layer outputs. Similar to\u00a0TensorFI 1, TensorFI 2 supports &hellip;<\/p>\n","protected":false},"author":8,"featured_media":0,"parent":1696,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"_genesis_hide_title":false,"_genesis_hide_breadcrumbs":false,"_genesis_hide_singular_image":false,"_genesis_hide_footer_widgets":false,"_genesis_custom_body_class":"","_genesis_custom_post_class":"","_genesis_layout":"","footnotes":""},"acf":[],"_links":{"self":[{"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/pages\/3643"}],"collection":[{"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/comments?post=3643"}],"version-history":[{"count":3,"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/pages\/3643\/revisions"}],"predecessor-version":[{"id":3727,"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/pages\/3643\/revisions\/3727"}],"up":[{"embeddable":true,"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/pages\/1696"}],"wp:attachment":[{"href":"http:\/\/cad4security.org\/index.php\/wp-json\/wp\/v2\/media?parent=3643"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}