Backdoors can be embedded in ResNet and ViT models as statistically indistinguishable latent directions, reducing cryptographic undetectability to an intractable hypothesis test over parameter distributions.
Backdoor attacks and defenses in computer vision domain: A survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Embedding and removing a dummy backdoor reduces unknown backdoor success in generative LLMs by targeting shared trigger-activated internal mechanisms.
citing papers explorer
-
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
Backdoors can be embedded in ResNet and ViT models as statistically indistinguishable latent directions, reducing cryptographic undetectability to an intractable hypothesis test over parameter distributions.
-
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs
Embedding and removing a dummy backdoor reduces unknown backdoor success in generative LLMs by targeting shared trigger-activated internal mechanisms.