I'm presenting our paper "Boosting Big Brother: Attacking Search Engines with Encodings" coauthored with @lucapajola, @iliaishacked, @rossjanderson, and @mauroconti_ at RAID at 4pm HKT today.
I'm honored that we were awarded the Best Paper Award for RAID 2023. Come check out the talk if you're here!
arxiv.org/abs/2304.14031
I鈥檓 presenting our paper "Trojan Source: Invisible Vulnerabilities" coauthored with @rossjanderson at USENIX Security at 1:30pm PT today. Come check it out! arxiv.org/abs/2111.00169
Uncommon Unicode encodings can be used to manipulate the results of search engines and their chatbot counterparts. If an adversary can manipulate a user into copying a search term into a search engine, they can leverage this behavior to control the results.
This work will appear in RAID 2023 this October and was done with coauthors Luca Pajola, @iliaishacked, @rossjanderson, and @mauroconti_.
Imperceptible adversarial examples have now arrived for NLP. Unicode can be used to perturb text encodings in a way that targets ML models without affecting humans. Our techniques can be used to attack systems ranging from toxic content detection to machine translation.
I鈥檓 presenting this work in a paper titled "Bad Characters: Imperceptible NLP Attacks" coauthored with @iliaishacked, @rossjanderson, and @NicolasPapernot at IEEE S&P at 10:40am PT today. Come check it out.
Nicholas Boucher retweeted
Having trouble remembering all your passwords? @HSEAS student has a new app for that hvrd.me/YWtNM

