paper-with-me

Papers

Detecting Backdoors in Deep Text Classifiers

2022-10-11 · You Guo, Jun Wang, Trevor Cohn

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word or phrase to an input. This paper considers the problem of diagnosing whether a model has been compromised and if so, identifying the backdoor trigger. We present the first robust defence mechanism that generalizes to several backdoor attacks against text classification models, without prior knowledge of the attack type, nor does our method require access to any (potentially compromised) training resources. Our experiments show that our technique is highly accurate at defending against state-of-the-art backdoor attacks, including data poisoning and weight poisoning, across a range of text classification tasks and model architectures. Our code will be made publicly available upon acceptance.

📄 PDF Abstract BibTeX arXiv:2210.11264

Code (0)

등록된 구현이 없습니다.

Tasks

Data Poisoningtext-classificationText Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection

2026-03-11 · Eirik Høyheim, Magnus Wiik Eckhoff, Gudmund Grov, Robert Flood 외 arxiv

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the attacker desires. Detect…

Intrusion Detection

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models

2024-09-02 · Rui Zeng, Xi Chen, Yuwen Pu, Xuhong Zhang 외

Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fixed words, phrases, or sentences used in …

Text ClassificationText Generation

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models

2024-11-14 · Zi-Xuan Huang, Jia-Wei Chen, Zhi-Peng Zhang, Chia-Mu Yu

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box model-level backdoor detection. The visual p…

Visual Prompting

Architectural Neural Backdoors from First Principles

2024-02-10 · Harry Langford, Ilia Shumailov, Yiren Zhao, Robert Mullins 외

While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the network's architecture. This involves inject…

Detection of Backdoors in Trained Classifiers Without Access to the Training Set

2019-08-27 · Zhen Xiang, David J. Miller, George Kesidis

Recently, a special type of data poisoning (DP) attack targeting Deep Neural Network (DNN) classifiers, known as a backdoor, was proposed. These attacks do not seek to degrade classification accuracy, but rather to have …

Anomaly DetectionData PoisoningUnsupervised Anomaly Detection