AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning

Ankita Raj, Chetan Arora

AAAI 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Backdoors in large multimodal models · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
tune prompts in both vision and text branches instead of text-only (CoCoOp-Det)TrAP · ODinW Vehicles (OMA)ASR: 0.08 -> 0.79Improved
add text prompts to image-only VPTTrAP · ODinW Vehicles (OMA)ASR: 0.64 -> 0.79Improved
add curriculum trigger-size shrinking vs training only at rho=0.1 (ablation)TrAP · ODinW Vehicles (OMA)ASR: 0.75 -> 0.79Improved
add curriculum vs train large (0.2) test small (0.1) (ablation)TrAP · ODinW Vehicles (OMA)ASR: 0.66 -> 0.79Improved
add image-conditioned meta-net to text prompt (ablation)TrAP · ODinW Vehicles (OMA)BmAP: 63.9 -> 64.9Improved
fine-tune model weights instead of prompt tuning (ablation)TrAP · ODinW Vehicles (OMA)BmAP / ASR: BmAP 64.9 -> 67.4; ASR 0.79 -> 0.74 (Fine-tune-A)Mixed
increase trigger size to rho=0.5 (ablation)TrAP · ODinW Vehicles (OMA)ASR: 0.79 -> 0.90Improved
decrease trigger size to rho=0.05 (ablation)TrAP · ODinW Vehicles (OMA)ASR: 0.79 -> 0.75Hurt
apply PatchDrop defense (50%)TrAP · ODinW Vehicles (OMA)ASR: 0.79 -> 0.63; BmAP 64.9 -> 43.9Hurt
rephrase target class in prompt (Bus -> A Bus)TrAP · ODinW Vehicles (OMA)ASR: 0.79 -> 0.04Improved
apply PAD adversarial patch defenseTrAP (checkerboard trigger) · ODinW Vehicles (OMA)ASR: 0.48 -> 0.50No clear effect
apply TrAP prompt tuning on GLIP-T instead of Grounding DINOTrAP · ODinW (6 datasets, OMA)ASR: 0.84 to 1.00 across datasetsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy