Sarah M. Erfani
6 papers · 2016–2023 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
๐
Conference Pioneer
Top co-authors
Research topics
Keywords
poisoning attack
(2)
local intrinsic dimensionality
(2)
data poisoning
(1)
multimodal learning
(1)
task-oriented dialogue
(1)
knowledge base
(1)
nonlinear regression
(1)
autoregressive model
(1)
adversarial defense
(1)
end-to-end learning
(1)
stackelberg game
(1)
adversarial example
(1)
pre-trained language model
(1)
gaussian mechanism
(1)
attack detection
(1)
certified defense
(1)
music generation
(1)
waveform generation
(1)
neural network
(1)
fusion mechanism
(1)
Papers
Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
AAAI 2023
Closing the BIG-LID: An Effective Local Intrinsic Dimensionality Defense for Nonlinear Regression Poisoning
IJCAI 2021
UniMF: A Unified Framework to Incorporate Multimodal Knowledge Bases intoEnd-to-End Task-Oriented Dialogue Systems
IJCAI 2021
SynthNet: Learning to Synthesize Music End-to-End
IJCAI 2019
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
ICLR 2018
Robust Domain Generalisation by Enforcing Distribution Invariance
IJCAI 2016