Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

poisoning-based backdoors

Poisoning-based backdoors are hidden vulnerabilities injected into a machine learning model by manipulating its training data to embed unauthorized behaviors. In this attack method, an adversary introduces modified training samples containing a specific trigger pattern paired with an attacker-chosen target label, causing the model to learn the malicious association alongside its intended task. Consequently, the trained model functions accurately on standard, clean inputs during normal deployment, but predictably alters its output to the predefined target class whenever the designated trigger appears in an input. This approach relies entirely on corrupting the training dataset during the learning phase, distinguishing it from attacks that directly modify a model architecture or manually alter its internal weights.

1 item

Handcrafted Backdoors in Deep Neural Networks

Handcrafted Backdoors in Deep Neural Networks

Sanghyun Hong, Nicholas Carlini, Alexey Kurakin

OrganizationsGoogleOregon State University

Why you should read this

Exposes a major blind spot in neural network security by directly editing model weights to insert stealthy backdoors without poisoning training data, bypassing standard defenses while maintaining high attack success rates and benign task accuracy.

When machine learning training is outsourced to third parties, backdoor attacks become practical as the third party who trains the model may act maliciously to inject hidden behaviors into the otherwise accurate model. Until now, the mechanism to inject backdoors has been limited to poisoning. We argue that a supply-chain attacker has more attack techniques available by introducing a handcrafted attack that directly manipulates a model's weights. This direct modification gives our attacker more degrees of freedom compared to poisoning, and we show it can be used to evade many backdoor detection or removal defenses effectively. Across four datasets and four network architectures our backdoor attacks maintain an attack success rate above 96%. Our results suggest that further research is needed for understanding the complete space of supply-chain backdoor attacks.

Added

2026-09-26