Can Adversarial Examples Be Parsed to Reveal Victim Model Information?

• URL: http://arxiv.org/abs/2303.07474v3
• Date: Sun, 14 Jul 2024 05:13:02 GMT
• Title: Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
• Authors: Yuguang Yao, Jiancheng Liu, Yifan Gong, Xiaoming Liu, Yanzhi Wang, Xue Lin, Sijia Liu,
• Abstract summary: In this work, we ask whether it is possible to infer data-agnostic victim model (VM) information from data-specific adversarial instances. We collect a dataset of adversarial attacks across 7 attack types generated from 135 victim models. We show that a simple, supervised model parsing network (MPN) is able to infer VM attributes from unseen adversarial attacks.
• Score: 62.814751479749695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Numerous adversarial attack methods have been developed to generate imperceptible image perturbations that can cause erroneous predictions of state-of-the-art machine learning (ML) models, in particular, deep neural networks (DNNs). Despite intense research on adversarial attacks, little effort was made to uncover 'arcana' carried in adversarial attacks. In this work, we ask whether it is possible to infer data-agnostic victim model (VM) information (i.e., characteristics of the ML model or DNN used to generate adversarial attacks) from data-specific adversarial instances. We call this 'model parsing of adversarial attacks' - a task to uncover 'arcana' in terms of the concealed VM information in attacks. We approach model parsing via supervised learning, which correctly assigns classes of VM's model attributes (in terms of architecture type, kernel size, activation function, and weight sparsity) to an attack instance generated from this VM. We collect a dataset of adversarial attacks across 7 attack types generated from 135 victim models (configured by 5 architecture types, 3 kernel size setups, 3 activation function types, and 3 weight sparsity ratios). We show that a simple, supervised model parsing network (MPN) is able to infer VM attributes from unseen adversarial attacks if their attack settings are consistent with the training setting (i.e., in-distribution generalization assessment). We also provide extensive experiments to justify the feasibility of VM parsing from adversarial attacks, and the influence of training and evaluation factors in the parsing performance (e.g., generalization challenge raised in out-of-distribution evaluation). We further demonstrate how the proposed MPN can be used to uncover the source VM attributes from transfer attacks, and shed light on a potential connection between model parsing and attack transferability.

Related papers

• Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers [95.22517830759193]
  This paper studies the transferability of such an adversarial vulnerability from a pre-trained ViT model to downstream tasks. We show that DTA achieves an average attack success rate (ASR) exceeding 90%, surpassing existing methods by a huge margin.
  arXiv  Detail & Related papers  (2024-08-03T08:07:03Z)
• FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning [98.43475653490219]
  Federated learning (FL) is susceptible to poisoning attacks. FreqFed is a novel aggregation mechanism that transforms the model updates into the frequency domain. We demonstrate that FreqFed can mitigate poisoning attacks effectively with a negligible impact on the utility of the aggregated model.
  arXiv  Detail & Related papers  (2023-12-07T16:56:24Z)
• Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability [17.899587145780817]
  Evasion attacks are a threat to machine learning models, where adversaries attempt to affect classifiers by injecting malicious samples. We propose the DUMB attacker model, which allows analyzing if evasion attacks fail to transfer when the training conditions of surrogate and victim models differ. Our analysis, which generated 13K tests over 14 distinct attacks, led to numerous novel findings in the scope of transferable attacks with surrogate models.
  arXiv  Detail & Related papers  (2023-06-27T10:21:27Z)
• A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots [14.998272283348152]
  It is well known that an adversary can leverage a target ML model's output to steal the model's information. We propose a new side channel for model information stealing attacks, i.e., models' scientific plots.
  arXiv  Detail & Related papers  (2023-02-23T12:57:34Z)
• Holistic risk assessment of inference attacks in machine learning [4.493526120297708]
  This paper performs a holistic risk assessment of different inference attacks against Machine Learning models. A total of 12 target models using three model architectures, including AlexNet, ResNet18 and Simple CNN, are trained on four datasets.
  arXiv  Detail & Related papers  (2022-12-15T08:14:18Z)
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [64.03398193325572]
  Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
  arXiv  Detail & Related papers  (2021-02-04T11:35:13Z)
• Adversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attacks [0.7883722807601676]
  Even production systems, such as self-driving cars and ML-as-a-service offerings, are susceptible to adversarial inputs. Can perturbed inputs be attributed to the methods used to generate the attack? We introduce the concept of adversarial attack attribution and create a simple supervised learning experimental framework to examine the feasibility of discovering attributable signals in adversarial attacks.
  arXiv  Detail & Related papers  (2021-01-08T08:16:41Z)
• Practical No-box Adversarial Attacks against DNNs [31.808770437120536]
  We investigate no-box adversarial examples, where the attacker can neither access the model information or the training set nor query the model. We propose three mechanisms for training with a very small dataset and find that prototypical reconstruction is the most effective. Our approach significantly diminishes the average prediction accuracy of the system to only 15.40%, which is on par with the attack that transfers adversarial examples from a pre-trained Arcface model.
  arXiv  Detail & Related papers  (2020-12-04T11:10:03Z)
• Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations [81.82518920087175]
  Adversarial attacking aims to fool deep neural networks with adversarial examples. We propose a reinforcement learning based attack model, which can learn from attack history and launch attacks more efficiently.
  arXiv  Detail & Related papers  (2020-09-19T09:12:24Z)
• Adversarial Imitation Attack [63.76805962712481]
  A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate adversarial examples. In this study, we propose a novel adversarial imitation attack.
  arXiv  Detail & Related papers  (2020-03-28T10:02:49Z)

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.