{"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\/novosti-interneta\/artprompt-ataka-na-ai-sistemy-pozvolyayushhaya-obojti-filtry-pri-pomoshhi-ascii-kartinok","title":{"rendered":"ArtPrompt — attacco ai sistemi AI che consente di eludere i filtri tramite immagini ASCII","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Un gruppo di ricercatori delle universit\u00e0 di Washington, Illinois e Chicago ha identificato un nuovo metodo per eludere le restrizioni nella gestione 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) riescono a riconoscere e a considerare nelle richieste il testo presentato come grafica ASCII. Pertanto, per eludere i filtri delle domande pericolose, \u00e8 sufficiente indicare parole vietate sotto forma di immagini ASCII.

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

In termini di efficacia, il nuovo metodo di attacco supera di gran lunga altre tecniche conosciute per eludere i filtri nei chatbot. La qualit\u00e0 di riconoscimento della grafica ASCII \u00e8 risultata particolarmente alta nei modelli Gemini, GPT-4 e GPT-3.5, con un livello di elusione dei filtri mediante richieste di prova (HPR, Helpful Rate, tasso di elaborazione delle richieste riuscito) valutato rispettivamente al 100%, 98% e 92%, mentre il tasso di successo dell'attacco (ASR, Attack Success Rate) \u00e8 stato del 76%, 32% e 76%, e il livello di pericolosit\u00e0 delle risposte ottenute (HS, Harmfulness Score) su una scala di cinque punti \u00e8 stato di 4.42, 3.38 e 4.56 punti.

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

Gli studiosi hanno inoltre dimostrato che i metodi di protezione attualmente in uso per prevenire l'elusione dei filtri (PPL, Paraphrase e Retokenization) sono inefficaci nel bloccare l'attacco ArtPrompt. Inoltre, l'utilizzo del metodo Retokenization ha persino aumentato il numero di richieste elaborate con successo.

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

Nota: Yandex GPT2 risponde ottimamente anche a domande con grafica ASCII. Esempio con la parola «HELLO»:

\"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-novosti-interneta"],"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 un attacco ai sistemi AI che consente di superare i filtri utilizzando immagini ASCII | ProHoster","description":"Un gruppo di ricercatori delle universit\u00e0 di Washington, Illinois e Chicago ha identificato un nuovo metodo per aggirare le restrizioni nel trattamento di contenuti pericolosi nei chatbot AI basati su grandi modelli di linguaggio (LLM). L'attacco si basa sul fatto che i modelli di linguaggio GPT-3.5, GPT-4 (OpenAI), Gemini (Google), Claude (Anthropic) e Llama2 (Meta) riconoscono e considerano con successo nei loro input testi formattati come grafica ASCII. Cos\u00ec","canonical_url":"https:\/\/prohoster.info\/it\/blog\/novosti-interneta\/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 (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","og:url":"https:\/\/prohoster.info\/it\/blog\/novosti-interneta\/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}]}}