◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Tudor Dumitras

17 papers hereh-index 336.2k citations111 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author3
  • last author12

Across the 15 of 17 papers where every author was matched, so the position is known.

fields
  • cs.CR11
  • cs.LG6

identity via Semantic Scholar / OpenAlex

activity
20162025
most citedTerminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks

103 citations · 193 across the 8 of their papers we have counts for

collaborators
Showing 2018 · cs.LGShow all

2 papers · 2 filters

cs.LG2018

Shallow-Deep Networks: Understanding and Mitigating Network Overthinking

Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras

We characterize a prevalent weakness of deep neural networks (DNNs)---overthinking---which occurs when a DNN can reach correct predictions before its final layer. Overthinking is c…

cs.LG2018

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

Ali Shafahi, W. Ronny Huang, Mahyar Najibi +4

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explo…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.