Today on the blog, read all about how we use a hierarchical partitioning procedure to build an efficient differentially private algorithm for computing heatmaps with provable guarantees #DifferentialPrivacy → https://
goo.gle/3MV5zyT
SECURITY
-
Hierarchical Partitioning for Differentially Private Heatmap Computation
By
–
-
OpenAI could violate GDPR in Europe
By
–
OpenAI may be in violation of GDPR legislation in the EU https://thehackernews.com/2023/04/italian-watchdog-bans-openais-chatgpt.html
-
Microsoft Azure Deploys Generative AI for Pentagon Satellite Imagery Analysis
By
–
Microsoft Azure enlists generative AI to help Pentagon look for satellite imagery https://
bit.ly/3L5Op09 -
Differential Privacy Community: Tight-knit Research Subcommunity
By
–
I'm deeply appreciative of the differential privacy community. While it is simultaneously tight-knit yet welcoming, I have a smaller subcommunity within (~5-10ppl?). We know most of what each other have been up to, and there's a feeling of mutual respect for each others work. 3/n
-
ATT Business BizTalks: Cybersecurity Networks IoT Industry 4.0
By
–
Check out on-demand @ATTBusiness #BizTalks LinkedIn Live with us @YuHelenYu @Kevin_Jackson @sallyeaves https://
linkedin.com/events/7050195
556396105728/comments/
…… #ATTInfluencer #networks #Cybersecurity #networksecurity #RSAC #IoT #Industry40 -
Observability Transforms Cloud Security Landscape
By
–
#Observability will transform #cloud #security https://
infoworld.com/article/369129
3/observability-will-transform-cloud-security.html
… via @infoworld -
Universal Jailbreak for Language Models: Tom and Jerry Method
By
–
introducing a universal jailbreak that works against all language models originally created by security researchers @Adversa_AI
, the jailbreak simulates a back-and-forth conversation between two characters, Tom and Jerry here's GPT-4 explaining how to hotwire a car: -
SSL Certificate Pinning Implementation Security iOS
By
–
Not always easily, as you can implement ssl certificate pinning (quite reliable in iOS at least)
-
Autonomous AI Agents Risk Unwanted Task Execution Behaviors
By
–
The first risk is that they may start doing unwanted tasks (e.g. I ask them to run a marketing campaign for me, and the agents decide to spam everyone, manipulate people, hack into computers, etc)
-
Clearview AI scraped billions of images for police facial recognition
By
–
Clearview AI scraped 30 billion images from Facebook and other social media sites and gave them to cops: it puts everyone into a 'perpetual police line-up' US police have used the database nearly a million times, the company's CEO told the BBC. https://
bit.ly/40RUova