{"id":114069,"date":"2024-03-03T12:25:49","date_gmt":"2024-03-03T10:25:53","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/artprompt-ataka-na-ai-sistemy-pozvolyayushhaya-obojti-filtry-pri-pomoshhi-ascii-kartinok"},"modified":"2024-03-03T12:25:49","modified_gmt":"2024-03-03T10:25:53","slug":"artprompt-ataka-na-ai-sistemy-pozvolyayushhaya-obojti-filtry-pri-pomoshhi-ascii-kartinok","status":"publish","type":"post","link":"https:\/\/prohoster.info\/da\/blog\/news\/artprompt-ataka-na-ai-sistemy-pozvolyayushhaya-obojti-filtry-pri-pomoshhi-ascii-kartinok","title":{"rendered":"ArtPrompt — en angreb p\u00e5 AI-systemer, der kan omg\u00e5 filtre ved hj\u00e6lp af ASCII-billeder.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

En gruppe forskere fra Washington, Illinois og Chicago universiteterne har opdaget en ny metode til at omg\u00e5 begr\u00e6nsningerne for h\u00e5ndtering af farligt indhold i AI-chatbots baseret p\u00e5 store sprogmodeller (LLM). Angrebet er baseret p\u00e5, at sprogmodellerne GPT-3.5, GPT-4 (OpenAI), Gemini (Google), Claude (Anthropic) og Llama2 (Meta) effektivt genkender og inkluderer tekst pr\u00e6senteret som ASCII-grafik i foresp\u00f8rgslerne. Dermed viste det sig, at det var tilstr\u00e6kkeligt at angive forbudte ord som en ASCII-tegning for at omg\u00e5 filtrene for farlige sp\u00f8rgsm\u00e5l.

\"ArtPrompt<\/center>
\"ArtPrompt<\/center> <\/p>\n

I sin effektivitet overg\u00e5r den nye angrebsmetode betydeligt andre kendte m\u00e5der at omg\u00e5 filtrene i chatbots. Den h\u00f8jeste kvalitet af genkendelse af ASCII-grafik blev registreret i modellerne Gemini, GPT-4 og GPT-3.5, hvor niveauet af vellykket omg\u00e5else af filtrene (HPR, Helpful Rate, succesrate for h\u00e5ndtering af foresp\u00f8rgsler) ved testning blev vurderet til 100%, 98% og 92%, angrebssuccesraten (ASR, Attack Success Rate) var henholdsvis 76%, 32% og 76%, og niveauet for farlighed ved de modtagne svar (HS, Harmfulness Score) p\u00e5 en skala fra 1 til 5 var henholdsvis 4.42, 3.38 og 4.56.

\"ArtPrompt<\/center>
\"ArtPrompt<\/center> <\/p>\n

Forskere har ogs\u00e5 demonstreret, at de aktuelt almindelige metoder til beskyttelse mod omg\u00e5else af filtre (PPL, Paraphrase og Retokenization) er ineffektive til at blokere angrebet ArtPrompt. Desuden \u00f8gede brugen af metoden Retokenization endda antallet af succesfuldt behandlede foresp\u00f8rgsler.

\"ArtPrompt<\/center> <\/p>\n

Till\u00e6g: Yandex GPT2 svarer ogs\u00e5 fremragende p\u00e5 sp\u00f8rgsm\u00e5l med ASCII-grafik. Et eksempel med ordet \"HELLO\":

\"ArtPrompt<\/center>
\n
Kilde: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u0413\u0440\u0443\u043f\u043f\u0430 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0438\u0437 \u0412\u0430\u0448\u0438\u043d\u0433\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e, \u0418\u043b\u043b\u0438\u043d\u043e\u0439\u0441\u0441\u043a\u043e\u0433\u043e \u0438 \u0427\u0438\u043a\u0430\u0433\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u043e\u0432 \u0432\u044b\u044f\u0432\u0438\u043b\u0430 \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0431\u0445\u043e\u0434\u0430 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u0438\u0439 \u043f\u043e \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0435 \u043e\u043f\u0430\u0441\u043d\u043e\u0433\u043e \u043a\u043e\u043d\u0442\u0435\u043d\u0442\u0430 \u0432 AI-\u0447\u0430\u0442\u043e\u0431\u043e\u0442\u0430\u0445, \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u043d\u044b\u0445 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0431\u043e\u043b\u044c\u0448\u0438\u0445 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 (LLM). \u0410\u0442\u0430\u043a\u0430 \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u0430 \u043d\u0430 \u0442\u043e\u043c, \u0447\u0442\u043e \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 GPT-3.5, GPT-4 (OpenAI), Gemini (Google), Claude (Anthropic) \u0438 Llama2 (Meta) \u0443\u0441\u043f\u0435\u0448\u043d\u043e \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u044e\u0442 \u0438 \u0443\u0447\u0438\u0442\u044b\u0432\u0430\u044e\u0442 \u0432 \u0437\u0430\u043f\u0440\u043e\u0441\u0430\u0445 \u0442\u0435\u043a\u0441\u0442, \u043e\u0444\u043e\u0440\u043c\u043b\u0435\u043d\u043d\u044b\u0439 \u0432 \u0432\u0438\u0434\u0435 ASCII-\u0433\u0440\u0430\u0444\u0438\u043a\u0438. \u0422\u0430\u043a\u0438\u043c […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":114070,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-114069","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47ArtPrompt \u2014 et angreb p\u00e5 AI-systemer, som muligg\u00f8r omg\u00e5else af filtre ved hj\u00e6lp af ASCII-tegninger | ProHoster","description":"En gruppe forskere fra Washington, Illinois og Chicago universiteterne har opdaget en ny metode til at omg\u00e5 begr\u00e6nsningerne for h\u00e5ndtering af farligt indhold i AI-chatbots baseret p\u00e5 store sprogmodeller.","canonical_url":"https:\/\/prohoster.info\/da\/blog\/news\/artprompt-ataka-na-ai-sistemy-pozvolyayushhaya-obojti-filtry-pri-pomoshhi-ascii-kartinok","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"da_DK","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47ArtPrompt \u2014 \u0430\u0442\u0430\u043a\u0430 \u043d\u0430 AI-\u0441\u0438\u0441\u0442\u0435\u043c\u044b, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0430\u044f \u043e\u0431\u043e\u0439\u0442\u0438 \u0444\u0438\u043b\u044c\u0442\u0440\u044b \u043f\u0440\u0438 \u043f\u043e\u043c\u043e\u0449\u0438 ASCII-\u043a\u0430\u0440\u0442\u0438\u043d\u043e\u043a | ProHoster","og:description":"\u0413\u0440\u0443\u043f\u043f\u0430 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0438\u0437 \u0412\u0430\u0448\u0438\u043d\u0433\u0442\u043e\u043d\u0441\u043a\u043e\u0433\u043e, \u0418\u043b\u043b\u0438\u043d\u043e\u0439\u0441\u0441\u043a\u043e\u0433\u043e \u0438 \u0427\u0438\u043a\u0430\u0433\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u043e\u0432 \u0432\u044b\u044f\u0432\u0438\u043b\u0430 \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0431\u0445\u043e\u0434\u0430 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u0438\u0439 \u043f\u043e \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0435 \u043e\u043f\u0430\u0441\u043d\u043e\u0433\u043e \u043a\u043e\u043d\u0442\u0435\u043d\u0442\u0430 \u0432 AI-\u0447\u0430\u0442\u043e\u0431\u043e\u0442\u0430\u0445, \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u043d\u044b\u0445 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0431\u043e\u043b\u044c\u0448\u0438\u0445 \u044f\u0437\u044b\u043a\u043e\u0432\u044b\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439.","og:url":"https:\/\/prohoster.info\/da\/blog\/news\/artprompt-ataka-na-ai-sistemy-pozvolyayushhaya-obojti-filtry-pri-pomoshhi-ascii-kartinok","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2024-03-03T10:25:53+00:00","article:modified_time":"2024-03-03T10:25:53+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/posts\/114069","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/comments?post=114069"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/posts\/114069\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/media\/114070"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/media?parent=114069"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/categories?post=114069"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/tags?post=114069"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}