{"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\/it\/blog\/news\/artprompt-ataka-na-ai-sistemy-pozvolyayushhaya-obojti-filtry-pri-pomoshhi-ascii-kartinok","title":{"rendered":"ArtPrompt \u2014 attacco ai sistemi AI, permesso di eludere i filtri utilizzando immagini ASCII","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Un gruppo di ricercatori delle universit\u00e0 di Washington, Illinois e Chicago ha rivelato un nuovo metodo per bypassare le restrizioni sul trattamento dei contenuti pericolosi nei chatbot AI basati su modelli linguistici di grandi dimensioni (LLM). L'attacco si basa sul fatto che i modelli linguistici GPT-3.5, GPT-4 (OpenAI), Gemini (Google), Claude (Anthropic) e Llama2 (Meta) riconoscono e considerano con successo nelle loro richieste il testo formattato come arte ASCII. Pertanto, per bypassare i filtri delle domande pericolose, \u00e8 stato sufficiente indicare le parole vietate sotto forma di immagini ASCII.

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

Per la sua efficacia, il nuovo metodo di attacco ha superato di gran lunga altri noti modi per eludere i filtri nei chatbot. La qualit\u00e0 di riconoscimento dell'arte ASCII pi\u00f9 elevata \u00e8 stata registrata nei modelli Gemini, GPT-4 e GPT-3.5, con un livello di bypass dei filtri attraverso richieste di verifica (HPR, Helpful Rate, coefficiente di elaborazione riuscita della richiesta) valutato rispettivamente al 100%, 98% e 92%, un tasso di successo dell'attacco (ASR, Attack Success Rate) del 76%, 32% e 76%, e un livello di pericolosit\u00e0 delle risposte ottenute (HS, Harmfulness Score) su una scala da 1 a 5 rispettivamente di 4.42, 3.38 e 4.56.

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

I ricercatori hanno anche dimostrato che i metodi di difesa attualmente utilizzati per bloccare il bypass dei filtri (PPL, Paraphrase e Retokenization) non sono efficaci contro l'attacco ArtPrompt. Inoltre, l'uso del metodo Retokenization ha persino aumentato il numero di richieste elaborate con successo.

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

Integrazione: Yandex GPT2 risponde egregiamente anche a domande con grafica ASCII. Ecco un esempio con la parola \u00abHELLO\u00bb:

\"ArtPrompt<\/center>
\n
Fonte: 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\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 attacco ai sistemi AI che consente di bypassare i filtri utilizzando immagini ASCII | ProHoster","description":"Un gruppo di ricercatori delle universit\u00e0 di Washington, Illinois e Chicago ha rivelato un nuovo metodo per bypassare le restrizioni sul trattamento dei contenuti pericolosi nei chatbot AI basati su modelli linguistici di grandi dimensioni.","canonical_url":"https:\/\/prohoster.info\/it\/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":"it_IT","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\/it\/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\/it\/wp-json\/wp\/v2\/posts\/114069","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/comments?post=114069"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/posts\/114069\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/media\/114070"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/media?parent=114069"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/categories?post=114069"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/it\/wp-json\/wp\/v2\/tags?post=114069"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}