Folgen
Nikhil Kandpal
Nikhil Kandpal
Computer Science Ph.D. Candidate, University of Toronto
Bestätigte E-Mail-Adresse bei cs.toronto.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Universal adversarial triggers for attacking and analyzing NLP
E Wallace, S Feng, N Kandpal, M Gardner, S Singh
arXiv preprint arXiv:1908.07125, 2019
8972019
Large language models struggle to learn long-tail knowledge
N Kandpal, H Deng, A Roberts, E Wallace, C Raffel
International Conference on Machine Learning, 15696-15707, 2023
3852023
Deduplicating training data mitigates privacy risks in language models
N Kandpal, E Wallace, C Raffel
International Conference on Machine Learning, 10697-10707, 2022
2342022
Backdoor attacks for in-context learning with language models
N Kandpal, M Jagielski, F Tramèr, N Carlini
arXiv preprint arXiv:2307.14692, 2023
662023
Music enhancement via image translation and vocoding
N Kandpal, O Nieto, Z Jin
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
182022
User inference attacks on large language models
N Kandpal, K Pillutla, A Oprea, P Kairouz, CA Choquette-Choo, Z Xu
arXiv preprint arXiv:2310.09266, 2023
142023
Git-theta: A git extension for collaborative development of machine learning models
N Kandpal, B Lester, M Muqeeth, A Mascarenhas, M Evans, V Baskaran, ...
International Conference on Machine Learning, 15708-15719, 2023
102023
User Inference Attacks on LLMs
N Kandpal, K Pillutla, A Oprea, P Kairouz, C Choquette-Choo, Z Xu
Socially Responsible Language Modelling Research, 2023
42023
AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
F Liu, N Kandpal, C Raffel
arXiv preprint arXiv:2411.15102, 2024
2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–9