We're publishing a report, co-authored with @CSETGeorgetown and @stanfordio
, analyzing how language models could be misused for disinformation and how to mitigate those risks.
SECURITY
-
Language Models Misuse for Disinformation: Risks and Mitigation
By
–
-
Cyber Resiliency for Operational Technology Q&A
By
–
Q&A on Cyber Resiliency for Operational Technology http://
ow.ly/RVzJ50MgOcA @Ox_CyberSec @cybersecboardrm via @fogoros #sponsored #fortinet_ics #cybersecurity #networksecurity #otsecurity -
The Zero Day Problem in Cybersecurity
By
–
The Zero Day Problem >> http://
ow.ly/JIp750LPfQX @Cyber_DueDil @cybersecboardrm via @fogoros #sponsored #fortinet_ics #cybersecurity #otsecurity -
Nearly 600 AI Tools Available Across 40 Categories
By
–
There are almost 600 tools on our site with 40+ categories for easy navigation
-
ChatGPT Text Detection Fails: New AI Detection Challenge
By
–
Texto escrito por ChatGPT hace unos días… NO LO DETECTA
-
Cybersecurity Insights Resonate Through Tech Radio Podcast
By
–
Many thanks for sharing, so pleased how this resonated
#CyberSecurity #Security #podcasts @techradiottt -
Company Faces Criticism for Alleged GDPR Non-Compliance
By
–
“This is not just unfair but clearly illegal,” Schrems said. “We are not aware of any other company that has tried to ignore the GDPR in such an arrogant way."
-
Thorough Mitigation for Prompt Injection in AI Systems
By
–
It’s premature to call prompt injection solved, but this is the most thorough mitigation I’ve seen yet.
-
Differential Privacy Results Beyond Pure DP Guarantees
By
–
Everything above is for pure (ε, 0)-DP. We also have results for (ε, δ)-DP. Also, the conversion from robustness to privacy is not always optimal, we have an example for sparse mean estimation. 11/n
-
Robust Algorithms Enable Private Algorithm Design
By
–
In our work, the main conceptual result shows the other direction: a robust algorithm can be used to design a private algorithm. 7/n