Gabryx412_
Gabryx412_2mo ago

Need help please

How can we design a machine learning model that is provably immune to all possible adversarial attacks without sacrificing accuracy or efficiency?
8 Replies
guninvalid over coax alliance
:MudWhat: uh you can try running it locally or you can do it without the machine learning and basically just build a normal chatbot
Gabryx412_
Gabryx412_OP2mo ago
I see what you mean, but I was referring to theoretical robustness as in, whether it’s possible to design a model that is provably immune to adversarial perturbations under any distribution
guninvalid over coax alliance
i feel like you don't understand the question you're asking you can make it probably immune to specific attacks which specific attacks are you trying to mitigate?
Gabryx412_
Gabryx412_OP2mo ago
Actually, I do understand the question it’s a theoretical one I’m not referring to robustness against a specific class of attacks like FGSM or PGD I mean true, provable immunity to all possible adversarial perturbations under any data distribution, without sacrificing model accuracy or efficiency As far as we know, that’s mathematically impossible unless you make extremely strong assumptions about the threat model or the data manifold
guninvalid over coax alliance
don't you also need to make assumptions about what accuracy even is? how are you going to measure how accurate a model is?
Gabryx412_
Gabryx412_OP2mo ago
When I said “without sacrificing accuracy,” I meant within the conventional empirical sense: maintaining comparable performance on clean, in-distribution data Even if we fix that definition, achieving provable immunity to all adversarial perturbations still seems theoretically impossible
guninvalid over coax alliance
i would agree also this probably isn't the right server to ask about this, this isn't a ML server
Gabryx412_
Gabryx412_OP2mo ago
True, thanks

Did you find this page helpful?