I'd add another circle to that diagram for the permissions of anyone else who authored text that made it into the context – which often means untrusted external attackers since it's so easy to sneak in malicious instructions for a lot of LLM systems
SECURITY
-
Tor Anniversary: 23 Years of Anonymous Communications Technology
By
–
23 years ago today Tor was launched by MIT students for anonymous communications: https://
bit.ly/4e4maef -
Federal Judge Orders OpenAI to Preserve ChatGPT Conversation Histories
By
–
BREAKING: Federal judge orders OpenAI to preserve ChatGPT conversation histories in a copyright case! Even if users ask for deletion or privacy laws demand it, OpenAI must keep those chats safe.
Business accounts are off the hook, for now. OpenAI says it’ll -
Algorithmic LLM Attacks: Early Research and Discoveries
By
–
One of my favorite early pares on this stuff was https://
llm-attacks.org which algorithmically discovered effective attacks like this one -
Adversarial Security: Beyond Robust to Absolute Protection
By
–
My problem is that "more robust" isn't good enough – if there's just a 1% route for an attack to get through an adversarial attacker will figure that out
-
System Instructions Security: User Prompts Can Override Safety Measures
By
–
No – instruction hierarchy doesn't close the hole completely, it's always possible for the user instructions to override the system instructions if they use the right tricks
-
Decision Fatigue Risk in Human AI System Approval
By
–
I'm really worried about decision fatigue – if you ask a human to approve every single step they're very likely to learn to just click "yes" without thinking – easy to catch them out if you try hard enough
-
Tech Giants Reinventing Cybersecurity for AI Agent Era
By
–
How Tech Giants Are Reinventing Cybersecurity For The AI Agent Era
#AI #AIio #AIInnovation #ML #DataScience #Futureofwork @fabiomoioli @pascal_bornet @alliekmiller @mattshumer_ @OfficialLoganK @jeremyphoward @GaryMarcus -
AI-Driven Video Intelligence Transforms Public Space Security Operations
By
–
How can AI make public spaces safer and easier to manage? NVIDIA and @Ipsotek will share how AI-driven video intelligence is transforming operations for security leaders, consultants, and infrastructure planners. Key takeaways:
· Common blockers + misconceptions in public -
1Password Integration with Comet Enhances Built-in Security
By
–
Today we’re announcing a partnership to bring 1Password to Comet, for built-in personal security without interruption.