Por ejemplo, me estáis compartiendo un vídeo donde se propone marcar los textos de ChatGPT de forma invisible para poder detectar que es artificial. El problema, como comenta aquí Jeremy, es que estos sistemas una vez creados, son muy fáciles de superar.
CYBERSECURITY
-
Frustration with AI tool, VPN potentially worth considering
By
–
Oh, that sounds super frustrating. Worth the VPN, potentially. This is some one powerful AI tool.
-
Security Paper Review Process Demands Increased Burden Reviewers
By
–
Besides the fact Im getting older, some reasons last year was more tiring:
– security papers are long! 13 two-column pages (vs 8 in ML)
– also, their revision process requires more commitment from reviewers
– more generally, labour expected from reviewers per paper is on the rise -
Top Digital Skills for Product Delivery in 2026
By
–
6 of the top #digital-age skills for product delivery >>> @PMInstitute via @MikeQuindazzi >>> #AI #IoT #DataAnalytics #DataScience #CloudComputing #CyberSecurity >>> Global #Megatrends Report: http://
shorturl.at/lJP17 -
AI Course: No Coverage on Proprietary Data Protection
By
–
Protecting your proprietary data when using the AI isn't something I cover in the course. I give away all my best prompts inside, and many others in the course community are already sharing their work as well. For advice on this specifically, you may need to look elsewhere
-
AI Personal Timeline: Tracking Goals While Preserving Privacy
By
–
3/Alon Halevy envisions AI capturing massive amounts of data from your daily life — photos, browsing, purchases — and fusing it into a personal timeline that helps you track and achieve your goals, while preserving privacy.
-
AI Solutions for Banking: Fraud Detection and Customer Relationships
By
–
Interested in how #AI can help the banking industry solve problems? Learn: Fraud Detection and Prevention Deepening Customer Relationships Tackling Mounting Regulations Emerging Competition Download our ebook for more https://
bit.ly/3vA4Rx9 -
CIO Priorities: Talent, Cybersecurity, and Modernization Assessment
By
–
Thanks to @tomloftus and the @CIOJournal team for this excellent assessment of #CIO priorities, including talent, cyber, modernization. Thanks to all who participated https://
cio.createsend1.com/t/d-e-ztdlull-
yhltuihhe-r/
…
@angusloten
@bellelin_
@IsabelleBiscuit
https://
cio.createsend1.com/t/d-e-ztdlull-
yhltuihhe-r/
… -
Prompt Injection Discovery and Attribution: A History Correction
By
–
A history correction: I am not the first to discover prompt injection. I was merely the first to do so and discuss it publicly. PI was discovered independently by multiple teams. The first was Preamble, an LLM security company, whose find predates mine by several months.