Multi-concept adversarial attacks

• URL: http://arxiv.org/abs/2110.10287v1
• Date: Tue, 19 Oct 2021 22:14:19 GMT
• Title: Multi-concept adversarial attacks
• Authors: Vibha Belavadi, Yan Zhou, Murat Kantarcioglu, Bhavani M. Thuraisingham
• Abstract summary: Test time attacks targeting a single ML model often neglect their impact on other ML models. We develop novel attack techniques that can simultaneously attack one set of ML models while preserving the accuracy of the other.
• Score: 13.538643599990785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As machine learning (ML) techniques are being increasingly used in many applications, their vulnerability to adversarial attacks becomes well-known. Test time attacks, usually launched by adding adversarial noise to test instances, have been shown effective against the deployed ML models. In practice, one test input may be leveraged by different ML models. Test time attacks targeting a single ML model often neglect their impact on other ML models. In this work, we empirically demonstrate that naively attacking the classifier learning one concept may negatively impact classifiers trained to learn other concepts. For example, for the online image classification scenario, when the Gender classifier is under attack, the (wearing) Glasses classifier is simultaneously attacked with the accuracy dropped from 98.69 to 88.42. This raises an interesting question: is it possible to attack one set of classifiers without impacting the other set that uses the same test instance? Answers to the above research question have interesting implications for protecting privacy against ML model misuse. Attacking ML models that pose unnecessary risks of privacy invasion can be an important tool for protecting individuals from harmful privacy exploitation. In this paper, we address the above research question by developing novel attack techniques that can simultaneously attack one set of ML models while preserving the accuracy of the other. In the case of linear classifiers, we provide a theoretical framework for finding an optimal solution to generate such adversarial examples. Using this theoretical framework, we develop a multi-concept attack strategy in the context of deep learning. Our results demonstrate that our techniques can successfully attack the target classes while protecting the protected classes in many different settings, which is not possible with the existing test-time attack-single strategies.

Related papers

• DALA: A Distribution-Aware LoRA-Based Adversarial Attack against Language Models [64.79319733514266]
  Adversarial attacks can introduce subtle perturbations to input data. Recent attack methods can achieve a relatively high attack success rate (ASR) We propose a Distribution-Aware LoRA-based Adversarial Attack (DALA) method.
  arXiv  Detail & Related papers  (2023-11-14T23:43:47Z)
• Can Adversarial Examples Be Parsed to Reveal Victim Model Information? [62.814751479749695]
  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.
  arXiv  Detail & Related papers  (2023-03-13T21:21:49Z)
• Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systems [0.7829352305480285]
  A growing number of researchers are recently investigating the feasibility of such attacks against machine learning-based security systems. This study was to investigate the actual feasibility of adversarial attacks, specifically evasion attacks, against network-based intrusion detection systems. Our goal is to create adversarial botnet traffic that can avoid detection while still performing all of its intended malicious functionality.
  arXiv  Detail & Related papers  (2023-03-12T14:01:00Z)
• MultiRobustBench: Benchmarking Robustness Against Multiple Attacks [86.70417016955459]
  We present the first unified framework for considering multiple attacks against machine learning (ML) models. Our framework is able to model different levels of learner's knowledge about the test-time adversary. We evaluate the performance of 16 defended models for robustness against a set of 9 different attack types.
  arXiv  Detail & Related papers  (2023-02-21T20:26:39Z)
• Btech thesis report on adversarial attack detection and purification of adverserially attacked images [0.0]
  This thesis report is on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc.
  arXiv  Detail & Related papers  (2022-05-09T09:24:11Z)
• Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios [22.22337220509128]
  Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. We propose a detection framework based on BP reverse-engineering and a novel it expected transferability (ET) statistic.
  arXiv  Detail & Related papers  (2022-01-20T22:21:38Z)
• Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples [107.38834819682315]
  We study a conceptually simple approach to defend few-shot classifiers against adversarial attacks. We propose a simple attack-agnostic detection method, using the concept of self-similarity and filtering. Our evaluation on the miniImagenet (MI) and CUB datasets exhibit good attack detection performance.
  arXiv  Detail & Related papers  (2021-10-24T05:46:03Z)
• From Zero-Shot Machine Learning to Zero-Day Attack Detection [3.6704226968275258]
  In certain applications such as Network Intrusion Detection Systems, it is challenging to obtain data samples for all attack classes that the model will most likely observe in production. In this paper, a zero-shot learning methodology has been proposed to evaluate the ML model performance in the detection of zero-day attack scenarios.
  arXiv  Detail & Related papers  (2021-09-30T06:23:00Z)
• 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)
• Leveraging Siamese Networks for One-Shot Intrusion Detection Model [0.0]
  Supervised Machine Learning (ML) to enhance Intrusion Detection Systems has been the subject of significant research. retraining the models in-situ renders the network susceptible to attacks owing to the time-window required to acquire a sufficient volume of data. Here, a complementary approach referred to as 'One-Shot Learning', whereby a limited number of examples of a new attack-class is used to identify a new attack-class. A Siamese Network is trained to differentiate between classes based on pairs similarities, rather than features, allowing to identify new and previously unseen attacks.
  arXiv  Detail & Related papers  (2020-06-27T11:40:01Z)
• Adversarial examples are useful too! [47.64219291655723]
  I propose a new method to tell whether a model has been subject to a backdoor attack. The idea is to generate adversarial examples, targeted or untargeted, using conventional attacks such as FGSM. It is possible to visually locate the perturbed regions and unveil the attack.
  arXiv  Detail & Related papers  (2020-05-13T01:38:56Z)

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.