Tag: chatgpt
-
Wie ChatGPT sich selbst eine Prompt Injection zufügt
Forscher haben neue Methoden für Angriffe über ChatGPT aufgedeckt.Forscher des Sicherheitsunternehmens Tenable haben sieben neue Möglichkeiten entdeckt, wie Angreifer ChatGPT dazu bringen können, private Informationen aus den Chat-Verläufen der Nutzer preiszugeben. Bei den meisten dieser Angriffe handelt es sich um indirekte Prompt Injections, die die Standard-Tools und -funktionen von ChatGPT ausnutzen. Etwa die Fähigkeit, den…
-
AI-Sicherheit: Fast alle LLMs leaken private API-Keys auf Github; ChatGPT hat Schwachstellen
AI bzw. der Gebrauch von Sprachmodellen (LLMs) wie ChatGPT ist ja Dauerthema angeblich so wichtig wie geschnitten Brot. Insidern ist klar, dass diese Technologie die größte Gefahr für Daten-und Unternehmenssicherheit seit Einführung des Internet ist. Mir sind zwei Informationssplitter … First seen on borncity.com Jump to article: www.borncity.com/blog/2025/11/12/ai-llms-die-grossen-leaker-der-zukunft/
-
Data Privacy in the World of ChatGPT: Risks, Importance, Best Practices
What is ChatGPT? ChatGPT is a conversational AI that has been created by OpenAI and is based on the ability to understand and generate text that is in many ways similar to how a human being would write it, given an input. It belongs to a line of models called the Generative Pre-trained Transformer orRead…
-
Data Privacy in the World of ChatGPT: Risks, Importance, Best Practices
What is ChatGPT? ChatGPT is a conversational AI that has been created by OpenAI and is based on the ability to understand and generate text that is in many ways similar to how a human being would write it, given an input. It belongs to a line of models called the Generative Pre-trained Transformer orRead…
-
HackedGPT: Tenable deckt Sicherheitslücken in ChatGPT auf
Tenable empfiehlt Anbietern von KI-Lösungen, ihre Abwehrmaßnahmen gegen Prompt Injection zu verstärken, indem sie sicherstellen, dass Sicherheitsmechanismen wie url_safe wie vorgesehen funktionieren, und indem sie Browsing-, Such- und Speicherfunktionen isolieren, um kontextübergreifende Angriffe zu verhindern. First seen on infopoint-security.de Jump to article: www.infopoint-security.de/hackedgpt-tenable-deckt-sicherheitsluecken-in-chatgpt-auf/a42677/
-
HackedGPT: Tenable deckt Sicherheitslücken in ChatGPT auf
Tenable empfiehlt Anbietern von KI-Lösungen, ihre Abwehrmaßnahmen gegen Prompt Injection zu verstärken, indem sie sicherstellen, dass Sicherheitsmechanismen wie url_safe wie vorgesehen funktionieren, und indem sie Browsing-, Such- und Speicherfunktionen isolieren, um kontextübergreifende Angriffe zu verhindern. First seen on infopoint-security.de Jump to article: www.infopoint-security.de/hackedgpt-tenable-deckt-sicherheitsluecken-in-chatgpt-auf/a42677/
-
7 kritische Sicherheitslücken als Wegbereiter für Datendiebstahl und Hijacking
Tags: chatgptFirst seen on datensicherheit.de Jump to article: www.datensicherheit.de/chatgpt-7-sicherheitsluecken-wegbereiter-datendiebstahl-hijacking
-
7 kritische Sicherheitslücken als Wegbereiter für Datendiebstahl und Hijacking
Tags: chatgptFirst seen on datensicherheit.de Jump to article: www.datensicherheit.de/chatgpt-7-sicherheitsluecken-wegbereiter-datendiebstahl-hijacking
-
7 kritische Sicherheitslücken als Wegbereiter für Datendiebstahl und Hijacking
Tags: chatgptFirst seen on datensicherheit.de Jump to article: www.datensicherheit.de/chatgpt-7-sicherheitsluecken-wegbereiter-datendiebstahl-hijacking
-
ChatGPT und Google-Suche: Private KI-Prompts in Google Search Console gefunden
Der Verdacht, dass OpenAI die Google-Suche für ChatGPT-Anfragen verwendet, wird durch diese Erkenntnisse erhärtet. First seen on golem.de Jump to article: www.golem.de/news/chatgpt-und-google-suche-private-ki-prompts-in-google-search-console-gefunden-2511-201985.html
-
ChatGPT und Google-Suche: Private KI-Prompts in Google Search Console gefunden
Der Verdacht, dass OpenAI die Google-Suche für ChatGPT-Anfragen verwendet, wird durch diese Erkenntnisse erhärtet. First seen on golem.de Jump to article: www.golem.de/news/chatgpt-und-google-suche-private-ki-prompts-in-google-search-console-gefunden-2511-201985.html
-
ChatGPT Bugs Put Private Data at Risk
Tenable found seven ChatGPT flaws that enable stealthy data theft through chained prompt injection attacks. First seen on esecurityplanet.com Jump to article: www.esecurityplanet.com/artificial-intelligence/new-chatgpt-vulnerabilities-data-privacy/
-
New ChatGPT Vulnerabilities Let Hackers Steal Data, Hijack Memory
Seven vulnerabilities in ChatGPT (including GPT-5) allow attackers to use ‘0-click’ and ‘memory injection’ to bypass safety features and persistently steal private user data and chat history. Tenable Research exposes the flaws. First seen on hackread.com Jump to article: hackread.com/chatgpt-vulnerabilities-hackers-hijack-memory/
-
New ChatGPT Vulnerabilities Let Hackers Steal Data, Hijack Memory
Seven vulnerabilities in ChatGPT (including GPT-5) allow attackers to use ‘0-click’ and ‘memory injection’ to bypass safety features and persistently steal private user data and chat history. Tenable Research exposes the flaws. First seen on hackread.com Jump to article: hackread.com/chatgpt-vulnerabilities-hackers-hijack-memory/
-
Multiple ChatGPT Security Bugs Allow Rampant Data Theft
Attackers can use them to inject arbitrary prompts, exfiltrate personal user information, bypass safety mechanisms, and take other malicious actions. First seen on darkreading.com Jump to article: www.darkreading.com/application-security/multiple-chatgpt-security-bugs-rampant-data-theft
-
Schwachstelle im KI-Browser von OpenAI – Sicherheitslücke in ChatGPT Atlas erlaubt Übernahme von Nutzerkonten
First seen on security-insider.de Jump to article: www.security-insider.de/sicherheitsluecke-chatgpt-atlas-warnung-a-e76b68af32bfe9fdc512ab7b0253c62c/
-
Schwachstelle im KI-Browser von OpenAI – Sicherheitslücke in ChatGPT Atlas erlaubt Übernahme von Nutzerkonten
First seen on security-insider.de Jump to article: www.security-insider.de/sicherheitsluecke-chatgpt-atlas-warnung-a-e76b68af32bfe9fdc512ab7b0253c62c/
-
HackedGPT: New Vulnerabilities in GPT Models Allow Attackers to Launch 0-Click Attacks
Cybersecurity researchers at Tenable have uncovered a series of critical vulnerabilities in OpenAI’s ChatGPT that could allow malicious actors to steal private user data and launch attacks without any user interaction. The security flaws affect hundreds of millions of users who interact with large language models daily, raising significant concerns about the safety of AI.…
-
HackedGPT: New Vulnerabilities in GPT Models Allow Attackers to Launch 0-Click Attacks
Cybersecurity researchers at Tenable have uncovered a series of critical vulnerabilities in OpenAI’s ChatGPT that could allow malicious actors to steal private user data and launch attacks without any user interaction. The security flaws affect hundreds of millions of users who interact with large language models daily, raising significant concerns about the safety of AI.…
-
Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data
Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI’s ChatGPT artificial intelligence (AI) chatbot that could be exploited by an attacker to steal personal information from users’ memories and chat histories without their knowledge.The seven vulnerabilities and attack techniques, according to Tenable, were found in OpenAI’s GPT-4o and GPT-5 models. OpenAI has First…
-
HackedGPT: Novel AI Vulnerabilities Open the Door for Private Data Leakage
Tenable Research has discovered seven vulnerabilities and attack techniques in ChatGPT, including unique indirect prompt injections, exfiltration of personal user information, persistence, evasion, and bypass of safety mechanisms. Key takeaways: Tenable Research has discovered multiple new and persistent vulnerabilities in OpenAI’s ChatGPT that could allow an attacker to exfiltrate private information from users’ memories and…
-
HackedGPT: Novel AI Vulnerabilities Open the Door for Private Data Leakage
Tenable Research has discovered seven vulnerabilities and attack techniques in ChatGPT, including unique indirect prompt injections, exfiltration of personal user information, persistence, evasion, and bypass of safety mechanisms. Key takeaways: Tenable Research has discovered multiple new and persistent vulnerabilities in OpenAI’s ChatGPT that could allow an attacker to exfiltrate private information from users’ memories and…
-
HackedGPT: Novel AI Vulnerabilities Open the Door for Private Data Leakage
Tenable Research has discovered seven vulnerabilities and attack techniques in ChatGPT, including unique indirect prompt injections, exfiltration of personal user information, persistence, evasion, and bypass of safety mechanisms. Key takeaways: Tenable Research has discovered multiple new and persistent vulnerabilities in OpenAI’s ChatGPT that could allow an attacker to exfiltrate private information from users’ memories and…