Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack

2023-01-05 · Tzvi Lederer, Gallil Maimon, Lior Rokach

Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that operates in clean-label, black-box settings, uses a stealthy poison and trigger and outperforms existing methods. We investigate the use of universal adversarial perturbations as triggers in clean-label attacks, following the success of such approaches under poison-label settings. We analyze the success of a naive adaptation and find that gradient alignment for crafting the poison is required to ensure high success rates. We conduct thorough experiments on MNIST, CIFAR10, and a reduced version of ImageNet and achieve state-of-the-art results.

📄 PDF Abstract BibTeX arXiv:2301.02615

Code (1)

tzvilederer/silent-killer 공식 구현 pytorch

Tasks

Backdoor AttackData Poisoning

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models

2026-01-20 · Bingxin Xu, Yuzhang Shang, Binghui Wang, Emilio Ferrara arxiv

Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundamental security flaw in modern VLA system…

Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers

2022-06-10 · Nan Luo, Yuanzhang Li, Yajie Wang, Shangbo Wu 외

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clea…

Backdoor Attack backdoor defense Vocal Bursts Valence Prediction

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics

2026-07-05 · Stefan Bühler, Mark Schutera arxiv

This work establishes that trigger-word data poisoning of vision language action models is practical, while at the same time the open-source robotics ecosystem holds trust assumptions about community contributions. A few…

Robustness of ML-Enhanced IDS to Stealthy Adversaries

2021-04-21 · Vance Wong, John Emanuello

Intrusion Detection Systems (IDS) enhanced with Machine Learning (ML) have demonstrated the capacity to efficiently build a prototype of "normal" cyber behaviors in order to detect cyber threats' activity with greater ac…

Anomaly Detection Intrusion Detection

Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference

2024-11-24 · Depeng Chen, Hao Chen, Hulin Jin, Jie Cui 외

Membership inference attacks (MIAs) are critical tools for assessing privacy risks and ensuring compliance with regulations like the General Data Protection Regulation (GDPR). However, their potential for auditing unauth…