Related papers: Backdoor Attacks on Multi-modal Contrastive Learning

Backdoor Attacks on Multi-modal Contrastive Learning

URL: http://arxiv.org/abs/2601.11006v1
Date: Fri, 16 Jan 2026 05:40:57 GMT
Title: Backdoor Attacks on Multi-modal Contrastive Learning
Authors: Simi D Kuniyilh, Rita Machacy,
Abstract summary: This paper offers a thorough and comparative review of backdoor attacks in contrastive learning.<n>It analyzes threat models, attack methods, target domains, and available defenses.<n>Our findings have significant implications for the secure deployment of systems in industrial and distributed environments.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Contrastive learning has become a leading self- supervised approach to representation learning across domains, including vision, multimodal settings, graphs, and federated learning. However, recent studies have shown that contrastive learning is susceptible to backdoor and data poisoning attacks. In these attacks, adversaries can manipulate pretraining data or model updates to insert hidden malicious behavior. This paper offers a thorough and comparative review of backdoor attacks in contrastive learning. It analyzes threat models, attack methods, target domains, and available defenses. We summarize recent advancements in this area, underline the specific vulnerabilities inherent to contrastive learning, and discuss the challenges and future research directions. Our findings have significant implications for the secure deployment of systems in industrial and distributed environments.

Related papers

Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey [21.4046846701173]
New attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged.<n>Existing surveys often target attack taxonomy and lack in-depth analysis.<n>This article addresses these gaps by offering a thorough summary of traditional and LVLM adversarial attacks.
arXiv Detail & Related papers (2024-10-31T07:22:51Z)
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks [58.824074124014224]
We show how contrastive backdoor attacks operate through distinctive mechanisms. Our findings highlight the need for defenses tailored to the specificities of contrastive backdoor attacks.
arXiv Detail & Related papers (2023-12-14T15:54:52Z)
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
arXiv Detail & Related papers (2023-11-20T02:21:49Z)
A reading survey on adversarial machine learning: Adversarial attacks and their understanding [6.1678491628787455]
Adversarial Machine Learning exploits and understands some of the vulnerabilities that cause the neural networks to misclassify for near original input. A class of algorithms called adversarial attacks is proposed to make the neural networks misclassify for various tasks in different domains. This article provides a survey of existing adversarial attacks and their understanding based on different perspectives.
arXiv Detail & Related papers (2023-08-07T07:37:26Z)
How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses [0.0]
This paper compiles the most recent adversarial attacks, grouped by the attacker capacity, and modern defenses clustered by protection strategies. We also present the new advances regarding Vision Transformers, summarize the datasets and metrics used in the context of adversarial settings, and compare the state-of-the-art results under different attacks, finishing with the identification of open issues.
arXiv Detail & Related papers (2023-05-18T10:33:28Z)
Untargeted Backdoor Attack against Object Detection [69.63097724439886]
We design a poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns.
arXiv Detail & Related papers (2022-11-02T17:05:45Z)
On the Effectiveness of Adversarial Training against Backdoor Attacks [111.8963365326168]
A backdoored model always predicts a target class in the presence of a predefined trigger pattern. In general, adversarial training is believed to defend against backdoor attacks. We propose a hybrid strategy which provides satisfactory robustness across different backdoor attacks.
arXiv Detail & Related papers (2022-02-22T02:24:46Z)
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses [150.64470864162556]
This work systematically categorizes and discusses a wide range of dataset vulnerabilities and exploits. In addition to describing various poisoning and backdoor threat models and the relationships among them, we develop their unified taxonomy.
arXiv Detail & Related papers (2020-12-18T22:38:47Z)
Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review [40.36824357892676]
This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected stage of the machine learning pipeline, the attack surfaces are recognized to be wide. Countermeasures are categorized into four general classes: blind backdoor removal, offline backdoor inspection, online backdoor inspection, and post backdoor removal.
arXiv Detail & Related papers (2020-07-21T12:49:12Z)
Backdoor Learning: A Survey [75.59571756777342]
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs) Backdoor learning is an emerging and rapidly growing research area. This paper presents the first comprehensive survey of this realm.
arXiv Detail & Related papers (2020-07-17T04:09:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.