pith. sign in

Title resolution pending

Effect of Finetuning Data Quantity We conduct experiments to investigate how much data an attacker needs to successfully poison the model

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Phantasia: Context-Adaptive Backdoors in Vision Language Models

cs.CV · 2026-04-09 · unverdicted · novelty 6.0

Phantasia is a new backdoor attack on VLMs that dynamically aligns malicious outputs with input context to achieve higher stealth and state-of-the-art success rates compared to static-pattern attacks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Phantasia: Context-Adaptive Backdoors in Vision Language Models cs.CV · 2026-04-09 · unverdicted · none · ref 41

    Phantasia is a new backdoor attack on VLMs that dynamically aligns malicious outputs with input context to achieve higher stealth and state-of-the-art success rates compared to static-pattern attacks.