TrojFlow: Flow Models are Natural Targets for Trojan Attacks
Flow-based generative models (FMs) have rapidly advanced as a method for mapping noise to data, its efficient training and sampling process makes it widely applicable in various fields. FMs can be viewed as a variant of diffusion models (DMs). At the same time, previous studies have shown that DMs are vulnerable to Trojan/Backdoor attacks, a type of output manipulation attack triggered by a maliciously embedded pattern at model input. We found that Trojan attacks on generative models are essentially equivalent to image transfer tasks from the backdoor distribution to the target distribution, the unique ability of FMs to fit any two arbitrary distributions significantly simplifies the training and sampling setups for attacking FMs, making them inherently natural targets for backdoor attacks. In this paper, we propose TrojFlow, exploring the vulnerabilities of FMs through Trojan attacks. In particular, we consider various attack settings and their combinations and thoroughly explore whether existing defense methods for DMs can effectively defend against our proposed attack scenarios. We evaluate TrojFlow on CIFAR-10 and CelebA datasets, our experiments show that our method can compromise FMs with high utility and specificity, and can easily break through existing defense mechanisms.
Code (0)
등록된 구현이 없습니다.
Tasks
SpecificityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets
Diffusion models have achieved great success in a range of tasks, such as image synthesis and molecule design. As such successes hinge on large-scale training data collected from diverse sources, the trustworthiness of t…
Image GenerationTrojan Detection in Large Language Models: Insights from The Trojan Detection Challenge
Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, but their vulnerability to trojan or backdoor attacks poses significant security risks. This paper explores the challenges and in…
Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications. Recently, the deployed DNNs have been demonstrated to be vulnerable to Trojan attacks, w…
TrojText: Test-time Invisible Textual Trojan Insertion
In Natural Language Processing (NLP), intelligent neuron models can be susceptible to textual Trojan attacks. Such attacks occur when Trojan models behave normally for standard inputs but generate malicious output for in…
SST-2Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learning
We present a Trojan (backdoor or trapdoor) attack that targets deep learning applications in wireless communications. A deep learning classifier is considered to classify wireless signals using raw (I/Q) samples as featu…
BIG-bench Machine LearningClassificationClusteringDeep Learning+2