{"id":553,"date":"2022-12-15T11:27:43","date_gmt":"2022-12-15T10:27:43","guid":{"rendered":"https:\/\/ai4cyber.eu\/?page_id=553"},"modified":"2025-10-23T21:01:01","modified_gmt":"2025-10-23T19:01:01","slug":"trustworthy-ai","status":"publish","type":"page","link":"https:\/\/ai4cyber.eu\/?page_id=553","title":{"rendered":"TRUSTWORTHY AI"},"content":{"rendered":"

[et_pb_section fb_built=”1″ admin_label=”Courses Hero” _builder_version=”4.14.8″ use_background_color_gradient=”on” background_color_gradient_start=”#0c71c3″ background_color_gradient_end=”#e01f45″ background_color_gradient_type=”radial” background_image=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2022\/10\/coding-background-texture.jpg” background_blend=”overlay” custom_padding=”100px|0px|180px|0px” animation_style=”slide” animation_direction=”top” animation_intensity_slide=”2%” locked=”off” global_colors_info=”{}”][et_pb_row _builder_version=”3.25″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”|||” custom_width_px=”1280px” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text _builder_version=”3.27.4″ header_font=”|on|||” header_font_size=”42px” header_line_height=”1.3em” background_size=”initial” background_position=”top_left” background_repeat=”repeat” text_orientation=”center” background_layout=”dark” max_width=”530px” module_alignment=”center” custom_padding=”|||” header_font_size_tablet=”” header_font_size_phone=”” header_font_size_last_edited=”on|desktop” locked=”off” global_colors_info=”{}”]<\/p>\n

TRUSTWORTHY AI<\/h1>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”TRUSTWORTHY AI” _builder_version=”4.14.8″ custom_padding=”0px|0px|0px|0px||” global_colors_info=”{}”][et_pb_row column_structure=”1_3,1_3,1_3″ admin_label=”Row” _builder_version=”4.14.8″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”|||” custom_padding=”0px|0px|27px|0px” global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”3.25″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_blurb title=”TRUST4AI.XAI – Explainability of AI ” url=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2025\/10\/AI4CYBER-TRUST4AI.XAI_.pdf” url_new_window=”on” image=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2022\/10\/coding-isometric-04.png” icon_placement=”left” content_max_width=”1100px” _builder_version=”4.14.8″ header_font=”|on|||” header_text_color=”#2e2545″ header_line_height=”1.5em” body_text_color=”#8585bd” body_font_size=”16px” body_line_height=”1.9em” background_color=”#ffffff” background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”-80px||10%|” custom_padding=”30px|40px|30px|40px” animation_style=”zoom” animation_direction=”bottom” animation_intensity_zoom=”20%” animation_starting_opacity=”100%” link_option_url_new_window=”on” hover_enabled=”0″ box_shadow_style=”preset2″ box_shadow_horizontal=”0px” box_shadow_vertical=”0px” box_shadow_blur=”60px” box_shadow_color=”rgba(71,74,182,0.12)” locked=”off” global_colors_info=”{}” sticky_enabled=”0″ link_option_url=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2025\/10\/AI4CYBER-TRUST4AI.XAI_.pdf”]<\/p>\n

A module to aid in explainability of supervised learning models.<\/p>\n

[\/et_pb_blurb][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”3.25″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_blurb title=”TRUST4AI.Fairness – Fairness of AI ” url=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2025\/10\/AI4CYBER-TRUST4AI.Fairness.pdf” url_new_window=”on” image=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2022\/10\/coding-isometric-04.png” icon_placement=”left” content_max_width=”1100px” _builder_version=”4.14.8″ header_font=”|on|||” header_text_color=”#2e2545″ header_line_height=”1.5em” body_text_color=”#8585bd” body_font_size=”16px” body_line_height=”1.9em” background_color=”#ffffff” background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”-80px||10%|” custom_padding=”30px|40px|30px|40px” animation_style=”zoom” animation_direction=”bottom” animation_intensity_zoom=”20%” animation_starting_opacity=”100%” link_option_url_new_window=”on” hover_enabled=”0″ box_shadow_style=”preset2″ box_shadow_horizontal=”0px” box_shadow_vertical=”0px” box_shadow_blur=”60px” box_shadow_color=”rgba(71,74,182,0.12)” locked=”off” global_colors_info=”{}” link_option_url=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2025\/10\/AI4CYBER-TRUST4AI.Fairness.pdf” sticky_enabled=”0″]<\/p>\n

A module to study fairness (bias) metrics and bias mitigations in AI models.<\/p>\n

[\/et_pb_blurb][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”3.25″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_blurb title=”TRUST4AI.Security – Security of AI ” url=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2025\/10\/AI4CYBER-TRUST4AI.Security.pdf” url_new_window=”on” image=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2022\/10\/coding-isometric-04.png” icon_placement=”left” content_max_width=”1100px” _builder_version=”4.14.8″ header_font=”|on|||” header_text_color=”#2e2545″ header_line_height=”1.5em” body_text_color=”#8585bd” body_font_size=”16px” body_line_height=”1.9em” background_color=”#ffffff” background_size=”initial” background_position=”top_left” background_repeat=”repeat” custom_margin=”-80px||10%|” custom_padding=”30px|40px|30px|40px” animation_style=”zoom” animation_direction=”bottom” animation_intensity_zoom=”20%” animation_starting_opacity=”100%” link_option_url_new_window=”on” hover_enabled=”0″ box_shadow_style=”preset2″ box_shadow_horizontal=”0px” box_shadow_vertical=”0px” box_shadow_blur=”60px” box_shadow_color=”rgba(71,74,182,0.12)” locked=”off” global_colors_info=”{}” link_option_url=”https:\/\/ai4cyber.eu\/wp-content\/uploads\/2025\/10\/AI4CYBER-TRUST4AI.Security.pdf” sticky_enabled=”0″]<\/p>\n

A solution to analyse adversarial machine learning (AML) threats and execute aversarial testing.<\/p>\n

[\/et_pb_blurb][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"

TRUSTWORTHY AIA module to aid in explainability of supervised learning models.A module to study fairness (bias) metrics and bias mitigations in AI models.A solution to analyse adversarial machine learning (AML) threats and execute aversarial testing.<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"class_list":["post-553","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=\/wp\/v2\/pages\/553","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=553"}],"version-history":[{"count":16,"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=\/wp\/v2\/pages\/553\/revisions"}],"predecessor-version":[{"id":2272,"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=\/wp\/v2\/pages\/553\/revisions\/2272"}],"wp:attachment":[{"href":"https:\/\/ai4cyber.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=553"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}