ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks

• URL: http://arxiv.org/abs/2210.00108v4
• Date: Fri, 1 Mar 2024 13:17:56 GMT
• Title: ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
• Authors: Tim Clifford, Ilia Shumailov, Yiren Zhao, Ross Anderson, Robert Mullins
• Abstract summary: We show that backdoors can be added during compilation, circumventing safeguards in the data preparation and model training stages. The attacker can not only insert existing weight-based backdoors during compilation, but also a new class of weight-independent backdoors, such as ImpNet. Some backdoors, including ImpNet, can only be reliably detected at the stage where they are inserted and removing them anywhere else presents a significant challenge.
• Score: 18.337267366258818
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by inspecting the training data, the model, or the integrity of the training procedure. In this work, we show that backdoors can be added during compilation, circumventing any safeguards in the data preparation and model training stages. The attacker can not only insert existing weight-based backdoors during compilation, but also a new class of weight-independent backdoors, such as ImpNet. These backdoors are impossible to detect during the training or data preparation processes, because they are not yet present. Next, we demonstrate that some backdoors, including ImpNet, can only be reliably detected at the stage where they are inserted and removing them anywhere else presents a significant challenge. We conclude that ML model security requires assurance of provenance along the entire technical pipeline, including the data, model architecture, compiler, and hardware specification.

Related papers

• Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models [68.40324627475499]
  We introduce a novel two-step defense framework named Expose Before You Defend. EBYD unifies existing backdoor defense methods into a comprehensive defense system with enhanced performance. We conduct extensive experiments on 10 image attacks and 6 text attacks across 2 vision datasets and 4 language datasets.
  arXiv  Detail & Related papers  (2024-10-25T09:36:04Z)
• Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor [0.24335447922683692]
  We introduce a new type of backdoor attack that conceals itself within the underlying model architecture. The add-on modules of model architecture layers can detect the presence of input trigger tokens and modify layer weights. We conduct extensive experiments to evaluate our attack methods using two model architecture settings on five different large language datasets.
  arXiv  Detail & Related papers  (2024-09-03T14:54:16Z)
• Flatness-aware Sequential Learning Generates Resilient Backdoors [7.969181278996343]
  Recently, backdoor attacks have become an emerging threat to the security of machine learning models. This paper counters CF of backdoors by leveraging continual learning (CL) techniques. We propose a novel framework, named Sequential Backdoor Learning (SBL), that can generate resilient backdoors.
  arXiv  Detail & Related papers  (2024-07-20T03:30:05Z)
• Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor [63.84477483795964]
  Data-poisoning backdoor attacks are serious security threats to machine learning models. In this paper, we focus on in-training backdoor defense, aiming to train a clean model even when the dataset may be potentially poisoned. We propose a novel defense approach called PDB (Proactive Defensive Backdoor)
  arXiv  Detail & Related papers  (2024-05-25T07:52:26Z)
• BackdoorBox: A Python Toolbox for Backdoor Learning [67.53987387581222]
  This Python toolbox implements representative and advanced backdoor attacks and defenses. It allows researchers and developers to easily implement and compare different methods on benchmark or their local datasets.
  arXiv  Detail & Related papers  (2023-02-01T09:45:42Z)
• Architectural Backdoors in Neural Networks [27.315196801989032]
  We introduce a new class of backdoor attacks that hide inside model architectures. These backdoors are simple to implement, for instance by publishing open-source code for a backdoored model architecture. We demonstrate that model architectural backdoors represent a real threat and, unlike other approaches, can survive a complete re-training from scratch.
  arXiv  Detail & Related papers  (2022-06-15T22:44:03Z)
• Anti-Backdoor Learning: Training Clean Models on Poisoned Data [17.648453598314795]
  Backdoor attack has emerged as a major security threat to deep neural networks (DNNs) We introduce the concept of emphanti-backdoor learning, aiming to train emphclean models given backdoor-poisoned data. We empirically show that ABL-trained models on backdoor-poisoned data achieve the same performance as they were trained on purely clean data.
  arXiv  Detail & Related papers  (2021-10-22T03:30:48Z)
• Check Your Other Door! Establishing Backdoor Attacks in the Frequency Domain [80.24811082454367]
  We show the advantages of utilizing the frequency domain for establishing undetectable and powerful backdoor attacks. We also show two possible defences that succeed against frequency-based backdoor attacks and possible ways for the attacker to bypass them.
  arXiv  Detail & Related papers  (2021-09-12T12:44:52Z)
• Black-box Detection of Backdoor Attacks with Limited Information and Data [56.0735480850555]
  We propose a black-box backdoor detection (B3D) method to identify backdoor attacks with only query access to the model. In addition to backdoor detection, we also propose a simple strategy for reliable predictions using the identified backdoored models.
  arXiv  Detail & Related papers  (2021-03-24T12:06:40Z)
• 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)
• Blind Backdoors in Deep Learning Models [22.844973592524966]
  We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than those in the prior literature. Our attack is blind: the attacker cannot modify the training data, nor observe the execution of his code, nor access the resulting model.
  arXiv  Detail & Related papers  (2020-05-08T02:15:53Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.