Hacker News new | past | comments | ask | show | jobs | submit login
Attacking Natural Language Processing Systems with Adversarial Examples (unite.ai)
37 points by tequila_shot on Dec 15, 2021 | hide | past | favorite | 4 comments



A new subfield of adversarial ML that considers similar challenges to adversarial NLP: topological attacks on graphs for attacking graph/node classifiers.

Both problems (NLP & graph robustness) are made much more challenging compared to adversarial robustness/attacks on image classifiers due to their combinatorial nature.

For graphs, canonical notions of robustness wrt classes of perturbations defined based on lp norms aren't so great (e.g. consider perturbing a barbell graph by removing a bridge edge- huge topological perturbation, but tiny lp perturbation!)

I think investigating robustness for graph classifiers should also help robustness for practical nlp systems and visa-versa. For example, is there any work that investigates robustness of nlp systems, but considers classes of perturbations defined on the space of ASTs?


I'm not going to fill out a Captcha just to see your website.


I always select bridges instead of traffic lights. I like to think I'm part of why Tesla's are phantom braking at bridges.


Is that what taxpayer research money is being used for? Oh gods. And I bet they bitch about not being able to get grants.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: