A lot of people who blame the world’s problems on misinformation tweeted feverishly about an obviously fabricated story about an AI drone attacking its operator
SECURITY
-
Microsoft Builds Quantum-Safe Future for Computing
By
–
Building a quantum-safe future – The Official Microsoft Blog Quantum computing at scale has the potential to help solve many of the world’s most complex and pressing problems. https://
bit.ly/3IRRvDu -
AI Generates 40,000 Chemical Weapon Molecules in Six Hours
By
–
AI suggested 40,000 new chemical weapons in just 6 hours. Researchers put AI normally used to search for helpful drugs into a “bad actor” mode to show how easily it could be abused. It found 40k lethal molecules in 6hrs. http://
theverge.com/2022/3/17/2298
3197/ai-new-possible-chemical-weapons-generative-models-vx
… -
AI-Controlled Drone Kills Operator in USAF Simulated Test
By
–
“We trained the system–‘Hey don’t kill the operator–that’s bad. You’re gonna lose points..’ So what does it start doing? It starts destroying the communication tower that the operator uses to communicate with the drone to stop it from killing the target.” https://
vice.com/en/article/4a3
3gj/ai-controlled-drone-goes-rogue-kills-human-operator-in-usaf-simulated-test
… -
Domino Unveils AI Safety Features for Responsible Model Lifecycle
By
–
#Rev4 keynote: Domino is committed to our customers unleashing AI safety and responsibility. With an integrated experience across the model lifecycle, we're addressing AI's unique challenges head-on. Excited to unveil new features for secure and ethical AI operation. #AI
-
ChatGPT Work Security: What Data Not to Share
By
–
What not to share with ChatGPT if you use it for work – turns out quite a lot ! #ai #ArtificialIntelligence #MachineLearning #deeplearning #chatgpt https://
buff.ly/45E4XVe -
Chrome Extensions Guardrails: Manifest V3 and Preprompt Requirements
By
–
It can. With chrome extensions you should add some guardrails. Ask for manifest v3.
Ask for content.js
Ask for manifest.js
We'll add these as preprompts later. -
ML Security: Closing the Gap Between Capabilities and Robustness
By
–
I've spent several years studying machine learning security with the goal of making ML reliable before it is used in more and more important contexts. Unfortunately, ML capabilities and adoption are growing much faster than ML robustness.
-
SGE displays TestingCatalog with source links
By
–
Here's is what SGE brings back about TestingCatalog. Source links are still shown on the right and they are quite big and noticable.
-
Microsoft President Identifies Deepfakes as Top AI Concern
By
–
Deepfakes are biggest Artificial Intelligence concern, says Microsoft president @microsoft #microsoft #fakenews #deepfakes #ai #ArtificialIntelligence #machinelearning #deeplearning https://
buff.ly/438CB3I