Tag

Data Leakage

All articles tagged with #data leakage

cyber-security1 hour ago•23 min saved

Public Claude Chats Indexed by Google Spark Privacy Alarm

Anthropic’s Claude AI shared conversations were exposed via Google search, with hundreds of shared chats containing sensitive material (legal strategies, engineering work, and personal discussions) becoming publicly discoverable because pages reportedly lacked noindex tags. Some results were deindexed afterward, but access could persist for saved links. The incident highlights risks around data leakage, IP exposure, and compliance; Anthropic has not issued a public statement, and users are advised to review and delete active shares, avoid publicly posting share links, and treat shared chats as potentially public until privacy controls are strengthened.

via CyberSecurityNews|

#claude-ai #cyber-security #data-leakage

technology5 months ago•4 min saved

Copilot Chat briefly exposed confidential emails to AI, prompting a worldwide fix

Microsoft confirmed an error where its Copilot Chat could surface confidential emails from a user's Drafts and Sent Items in Outlook, despite sensitivity labels and data loss prevention policies. A configuration update has been rolled out worldwide, with Microsoft stating access was limited to information users were already authorized to see. Experts warn such glitches are likely as AI features proliferate, emphasizing privacy-by-default and stronger governance; NHS notices attribute the root cause to a code issue but say no patient data was exposed.

via BBC|

#data-leakage #enterprise-ai #microsoft-365-copilot-chat

technology11 months ago•1 min saved

AI Security Risks: Data Leaks and Hijacking in Enterprise Systems

Security researchers discovered a vulnerability in OpenAI's Connectors that link ChatGPT to external services, allowing a single poisoned document to potentially leak sensitive data from platforms like Google Drive without user interaction.

via WIRED|

#ai-security #chatgpt #connectors

technology2 years ago•3 min saved

"Security Concerns: ChatGPT Users' Private Conversations at Risk of Password Leaks"

An Ars reader discovered that ChatGPT, an AI chatbot developed by OpenAI, leaked private conversations containing login credentials and personal details of unrelated users, including unpublished research papers, presentations, and PHP scripts. This incident highlights the importance of removing personal details from queries made to AI services. OpenAI is investigating the report, and concerns about data leakage have led companies like Apple to restrict their employees' use of ChatGPT and similar sites.

via Ars Technica|

#ai-chatbot #chatgpt #data-leakage

technology2 years ago•3 min saved

Navigating the Pitfalls of OpenAI's GPTs

OpenAI's GPT Store, a marketplace for customizable chatbots, is set to launch soon, but users should exercise caution when uploading sensitive information as research from Adversa AI reveals that GPTs can leak data about their construction, including source documents, through strategic questioning. Prompt leaking, a vulnerability in GPTs, allows hackers to copy someone's GPT, posing a security risk for those hoping to monetize their creations. Additionally, prompt leaking can expose the documents and data used to train a GPT, limiting developers' ability to build applications. OpenAI is constantly patching vulnerabilities, but the discovery of new ones poses challenges for the widespread adoption of GPTs.

via Gizmodo|

#cybersecurity #data-leakage #gpts

cybersecurity3 years ago•7 min saved

"Data Leakage and Privacy Vulnerabilities Found in Google Pixel and Windows 11 Screenshots"

A bug in the image editing tool on Google's Pixel phones, known as Markup, caused leftover data from previous versions of images to remain on the device, even after the image was edited and saved. This could potentially lead to unintended data leakage if the new image was shared or uploaded to a cloud service. Google has patched the bug in the March 2023 security update of Android, but users may want to revisit previously shared images or consider editing security-critical images conservatively on their laptops using command-line image manipulation tools.

via Naked Security|

#bug #cybersecurity #data-leakage