SECURITY

→ View original post on X — @deeplearn007

AI Policy: Balancing Competition, Security, Privacy and Sustainability

By

@deeplearn007

–

18 April 2024 11h55

Policy makers should consider the interactions between AI, data, competition law, security/privacy & carbon/ climate/ energy policy. There are emerging techniques that help address these issues such as Federated Learning w/Differential Privacy;
RAG w/LLMs;
Context based

→ View original post on X — @ryan_browne_

Cisco Launches HyperShield AI Security Product After Splunk Deal

By

@ryan_browne_

–

18 April 2024 9h10

Cisco is launching a new AI-focused security product, called HyperShield, on the back of its $28bn Splunk deal. “We’re moving from a world of scarcity to a world of abundance, with digital AI assistants for everything,” @jpatel41 told CNBC.

Open Source Models Prompt Injection Security Flaw

By

–

18 April 2024 4h46

Yeah, I wouldn't trust that! That does highlight interesting flaw in a lot of open models though: I think there are some models that use strings like [INST] without even reserving a token for them, which opens up all sorts of additional potential prompt injection mischief

Document Upload Transparency and AI Processing Visibility

By

–

18 April 2024 1h07

I want to know exactly what happens to documents I upload to it – how they are split and chunked, how text is extracted from PDFs, what gets embedded and stored, and what gets retrieved and included in prompts (Ideally I'd like a debug interface that lets me see it for myself)

→ View original post on X — @mer__edith

Privacy and Free Expression in AI: Critical Concerns

By

@mer__edith

–

17 April 2024 23h55

For anyone who cares about privacy and free expression, this is really important

Prompt Injection Threats Against GPT Wrapper Applications

By

–

17 April 2024 19h22

GPT wrapper apps are exactly the things that need to worry about prompt injection – it's not an attack against the models, it's an attack against applications built on top of the models

→ View original post on X — @bobgourley

Hacker Terminology: Distinguishing Ethical Hackers from Criminals

By

@bobgourley

–

17 April 2024 18h36

You pretty much stepped in it. Try this naming taxonomy: All hackers are good. Criminals are not hackers, they are criminals. Don't call criminals black hat hackers, call them criminals.

Mitigations Against Prompt Injection Attacks

By

–

17 April 2024 1h18

What mitigations do you have in place against prompt injection attacks?