WARPTECHNEWS · LAB
HomeAIBusinessTechArchive
WARPTECH LAB NEWS

Warptech Lab News aggrega le notizie più rilevanti da oltre 700 fonti internazionali, con classificazione AI, TL;DR sintetici e timeline cluster su singole storie.

Navigazione

  • Home
  • Archivio
  • Editor's Brief
  • Cerca
  • Il tuo account
  • Newsletter tech/AI

Informazioni legali

  • Privacy Policy
  • Termini di servizio
  • Cookie Policy

© 2026 Sparktech S.R.L. — Tutti i diritti riservati. Sito gestito e manutenuto da Sparktech S.R.L.

Sede legale: Corso Libertà 55, 13100 Vercelli (VC), Italia · P.IVA / C.F. 02835910023 · Contatti: admin@warptechlab.com

Home
Storia in 16 fonti

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks | TechCrunch

Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

Raccontata daneowin.netnewsbytesapp.comthehackernews.comtechcrunch.comdev.tothenextweb.comgizmodo.comthe-decoder.comeconomictimes.indiatimes.comhwupgrade.itgadgetsnow.indiatimes.comt3n.de+4 altre

Confronto fonti

6 prospettive sulla stessa storia
AI · summaries
techcrunch.comStai leggendo5 g fa

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks | TechCrunch

Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

originale
thenextweb.com4 g fa

OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks

OpenAI launched Lockdown Mode disabling live browsing, agent mode, and downloads to block prompt injection attacks on ChatGPT. Trades capabilities for security—vital for sensitive workflows but signals prompt injection as a frontier risk across all LLMs.

Leggi questa versione → originale
newsbytesapp.com5 g fa

OpenAI's new feature protects you from prompt injection attacks

OpenAI has launched Lockdown Mode, an optional feature aimed at safeguarding users from prompt injection attacks, a growing threat targeting conversational AI systems.

Leggi questa versione → originale
the-decoder.com4 g fa

ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt…

OpenAI enables Lockdown Mode to block prompt injection attacks on ChatGPT by disabling web access and Agent capabilities for users with sensitive data. Prompt injection is unsolved since GPT-3; the feature signals teams need organizational RBAC and governance—not features alone—to safely manage financial or proprietary data in LLMs.

Leggi questa versione → originale
gizmodo.com4 g fa

OpenAI Announces Unnerving New ChatGPT Feature Named 'Lockdown Mode'

OpenAI launched Lockdown Mode, disabling web browsing, images, agents, and file access to prevent prompt injection attacks and data theft from ChatGPT. The move signals LLMs aren't secure enough for sensitive data, raising governance concerns for enterprises using AI with legal or healthcare information.

Leggi questa versione → originale
thehackernews.com5 g fa

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

OpenAI Lockdown Mode limits outbound ChatGPT requests to reduce prompt injection data exfiltration risk for eligible accounts.

Leggi questa versione → originale

Timeline cronologica

  1. sabato 6 giugno 2026·neowin.net

    OpenAI is now rolling out Lockdown Mode to more ChatGPT users

    Originally restricted to enterprise executives and security teams, OpenAI is now expanding its Lockdown Mode to all ChatGPT users worldwide.

  2. sabato 6 giugno 2026·newsbytesapp.com

    OpenAI's new feature protects you from prompt injection attacks

    OpenAI has launched Lockdown Mode, an optional feature aimed at safeguarding users from prompt injection attacks, a growing threat targeting conversational AI systems.

  3. sabato 6 giugno 2026·thehackernews.com

    New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

    OpenAI Lockdown Mode limits outbound ChatGPT requests to reduce prompt injection data exfiltration risk for eligible accounts.

  4. sabato 6 giugno 2026·techcrunch.com

    OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks | TechCrunch

    Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

  5. domenica 7 giugno 2026·dev.to

    OpenAI Built a Lockdown Mode Because Tool-Based Data Exfiltration Is Real — Here's What Catches It Earlier

    OpenAI doesn't ship defensive product features out of nowhere. When they announced Lockdown Mode for...

  6. domenica 7 giugno 2026·thenextweb.com

    OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks

    ChatGPT's new Lockdown Mode disables live browsing, agent mode, and deep research to stop attackers from stealing data through prompt injection.

  7. domenica 7 giugno 2026·gizmodo.com

    OpenAI Announces Unnerving New ChatGPT Feature Named 'Lockdown Mode'

    "Lockdown Mode is not intended for everyone," OpenAI's blog post says. In other words, you're probably not important enough.

  8. domenica 7 giugno 2026·the-decoder.com

    ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection

    OpenAI's new Lockdown Mode for ChatGPT disables web access, Deep Research, and Agent Mode to make data theft through prompt injection attacks harder. The mode doesn't fully…

  9. domenica 7 giugno 2026·economictimes.indiatimes.com

    OpenAI rolls out Lockdown Mode for users handling sensitive information - The Economic Times

    OpenAI has launched Lockdown Mode to combat prompt injection attacks, a security feature designed for users handling sensitive data. This mode restricts live web browsing and…

  10. domenica 7 giugno 2026·hwupgrade.it

    Lockdown Mode cambia il volto di ChatGPT: più privacy, meno libertà operativa

    OpenAI ha avviato il rilascio di Lockdown Mode, una nuova modalit� di sicurezza per ChatGPT pensata per limitare i rischi di esfiltrazione dei dati attraverso attacchi di prompt…

  11. lunedì 8 giugno 2026·gadgetsnow.indiatimes.com

    OpenAI's new ChatGPT Lockdown Mode takes aim at one of AI's biggest security challenges

    Find latest technology news, gadgets reviews & ratings. Popular & latest gadgets specifications, features, prices, photos & videos. Trending mobile phone comparisons, slideshows,…

  12. lunedì 8 giugno 2026·t3n.de

    ChatGPT sichert Nutzer: Was der Lockdown-Mode bringt – und wovor er nicht schützt | t3n

    Mit einem neuen Lockdown-Modus sollen ChatGPT und damit auch eure Daten besser vor Attacken von Dritten geschützt werden. Welche großen Gefahren für Chatbots mit dem Modus…

  13. lunedì 8 giugno 2026·securityweek.com

    OpenAI Rolling Out ChatGPT Account Security Controls

    OpenAI is making two ChatGPT security controls more widely available, giving users additional tools to protect their accounts and data.

  14. lunedì 8 giugno 2026·infobae.com

    OpenAI despliega el Modo de Bloqueo para proteger a ChatGPT de los ataques de inyección de 'prompts'

    OpenAI despliega el Modo de Bloqueo para proteger a ChatGPT de los ataques de inyección de 'prompts'

  15. lunedì 8 giugno 2026·zdnet.com

    How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)

    The goal is to protect you against attackers who try to steal your personal data through prompt injection. But it does limit your ability to access the web.

  16. martedì 9 giugno 2026·heise.de

    ChatGPT sichert Nutzer: Was der Lockdown-Mode bringt und wovor er nicht schützt

    Neuer Lockdown-Modus soll ChatGPT und eure Daten besser vor Attacken von Dritten schützen. Welche Gefahren gestoppt werden und wo immer noch Risiken bestehen.