ROI coding enables backdoor triggers to survive lossy compression by embedding malicious information into binary bitstreams via sample-specific or customized masks for both learned and traditional codecs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DarkLLM trains an LLM to generate language-driven adversarial perturbations that unify targeted, untargeted, segmentation, and multi-model attacks on foundation models.
citing papers explorer
-
Inevitable Encounters: Backdoor Attacks Involving Lossy Compression
ROI coding enables backdoor triggers to survive lossy compression by embedding malicious information into binary bitstreams via sample-specific or customized masks for both learned and traditional codecs.
-
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
DarkLLM trains an LLM to generate language-driven adversarial perturbations that unify targeted, untargeted, segmentation, and multi-model attacks on foundation models.