Phantom: Physical Object Interactions as Dynamic Triggers for NMS-Exploited Backdoors

Tianlin Huo Dong-Chuan Ran Ranjie Duan Yaowei Zhu Peilun Du Ningbo Yao Huan-Qian Yan Xue Han Qiang Yun Yu-Zheng Tan Yang Bao Yuan He

· 0 citations · 32 references

TL;DR

A novel backdoor attack that leverages dynamic object interactions in realistic scenarios to activate malicious behavior by hijacking the Non-Maximum Suppression process in object detectors is proposed, demonstrating robust effectiveness.

Semantic Scholar

View source

Similar papers

#artificial intelligence Preprint Aug 2026

Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift

DistScan is presented, a backdoor detection framework based on a simple but previously unexploited observation: backdoor injection systematically shifts a model's pre-NMS prediction class distribution away from its training class frequencies, even on clean inputs without any trigger present.

Long-Tian Wang, Zheng-Yu Zhao, Chen-Hao Lin et al. · 0 citations

Preprint Sep 2026

ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus

ODPure is proposed, a novel input-stage black-box defense for object detection, which is based on input purification that ensures stable perception flows and provides robust defense against diverse backdoor attacks and trigger types while preserving baseline accuracy.

Li Zeng, Ming-Cheng Duan, Long-Fei Fan et al. · 0 citations

Preprint Aug 2026

Low-ASR Backdoors: Exploiting Attack Success Rate Reduction and Attacker-Defender Asymmetry

A reverse-training framework is introduced that weakens the trigger-target association, producing low-ASR backdoor models while preserving clean-input performance and exposing a fundamental attacker-defender asymmetry in existing defense paradigms.

Arham Riaz, Ting Yu · 0 citations

Preprint Aug 2026

Z-PEFT: Zero-shot Backdoor Detection in Parameter-Efficient Fine-Tuning via Canonical Spectral Signatures

This work proposes Z-PEFT, a lightweight meta-classifier that relies exclusively on layer-wise spectral measures for classification, and achieves the best performance while maintaining low and scalable computational cost among weight-space detectors.

Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni et al. · 0 citations

Preprint Sep 2026

RAMP: Reversing Adversarial Perturbations to Strengthen Clean-Label Backdoor Attacks against Malware Detectors

RAMP is proposed, an attack enhancement method that uses a genetic algorithm to optimize reversed adversarial perturbations under black-box access and then injects them through functionality-preserving binary manipulations, which substantially improves attack effectiveness over trigger-only baselines.

Jin-Wen Xin, Dong-Ni Zhang, Chen-Yang Wang et al. · 0 citations

Open access Sep 2026

ArchLock: Dynamic-Target Architectural Backdoor with Correlation-Based Statistical Triggers

ArchLock is proposed, a dynamic-target architectural backdoor framework designed exclusively for stateful inference deployments that maintain persistent mutable state across requests that exhibits robustness against fine-tuning and pruning and evades three behavioral detectors under the stated stateful deployment assum...

Qing-Song Xie, Yu-Wei Li, Qian Chen et al. · Electronics · 0 citations