Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection

• URL: http://arxiv.org/abs/2407.12292v1
• Date: Wed, 17 Jul 2024 03:24:09 GMT
• Title: Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection
• Authors: Youheng Sun, Shengming Yuan, Xuanhan Wang, Lianli Gao, Jingkuan Song,
• Abstract summary: GAKer is able to construct adversarial examples to any target class. Our method achieves an approximately $14.13%$ higher attack success rate for unknown classes.
• Score: 83.72430401516674
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Targeted adversarial attack, which aims to mislead a model to recognize any image as a target object by imperceptible perturbations, has become a mainstream tool for vulnerability assessment of deep neural networks (DNNs). Since existing targeted attackers only learn to attack known target classes, they cannot generalize well to unknown classes. To tackle this issue, we propose $\bf{G}$eneralized $\bf{A}$dversarial attac$\bf{KER}$ ($\bf{GAKer}$), which is able to construct adversarial examples to any target class. The core idea behind GAKer is to craft a latently infected representation during adversarial example generation. To this end, the extracted latent representations of the target object are first injected into intermediate features of an input image in an adversarial generator. Then, the generator is optimized to ensure visual consistency with the input image while being close to the target object in the feature space. Since the GAKer is class-agnostic yet model-agnostic, it can be regarded as a general tool that not only reveals the vulnerability of more DNNs but also identifies deficiencies of DNNs in a wider range of classes. Extensive experiments have demonstrated the effectiveness of our proposed method in generating adversarial examples for both known and unknown classes. Notably, compared with other generative methods, our method achieves an approximately $14.13\%$ higher attack success rate for unknown classes and an approximately $4.23\%$ higher success rate for known classes. Our code is available in https://github.com/VL-Group/GAKer.

Related papers

• NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian Noise [0.19820694575112383]
  Backdoor attacks pose a significant threat when using third-party data for deep learning development. We introduce a novel sample-specific multi-targeted backdoor attack, namely NoiseAttack. This work is the first of its kind to launch a vision backdoor attack with the intent to generate multiple targeted classes.
  arXiv  Detail & Related papers  (2024-09-03T19:24:46Z)
• OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection [18.11795712499763]
  This study proposes a novel one-class classification framework called One-class Graph Embedding Classification (OCGEC) OCGEC uses GNNs for model-level backdoor detection with only a little amount of clean data. In comparison to other baselines, it achieves AUC scores of more than 98% on a number of tasks.
  arXiv  Detail & Related papers  (2023-12-04T02:48:40Z)
• General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments [75.58342268895564]
  We use Deep Generative Networks (DGNs) with a novel training mechanism to eliminate the distribution gap. The trained DGNs align the distribution of adversarial samples with clean ones for the target DNNs by translating pixel values. Our strategy demonstrates its unique effectiveness and generality against black-box attacks.
  arXiv  Detail & Related papers  (2022-12-11T01:51:31Z)
• Gradient Concealment: Free Lunch for Defending Adversarial Attacks [18.98319703484334]
  We propose a plug-and-play layer that is training-free, concealing the vulnerable direction of gradient while guaranteeing the classification accuracy during the inference time. GCM reports superior defense results on the ImageNet classification benchmark, improving up to 63.41% top-1 attack (AR) when faced with adversarial inputs. We use GCM in the CVPR 2022 Robust Classification Challenge, currently achieving textbf2nd place in Phase II with only a tiny version of ConvNext.
  arXiv  Detail & Related papers  (2022-05-21T15:02:56Z)
• Discriminator-Free Generative Adversarial Attack [87.71852388383242]
  Agenerative-based adversarial attacks can get rid of this limitation. ASymmetric Saliency-based Auto-Encoder (SSAE) generates the perturbations. The adversarial examples generated by SSAE not only make thewidely-used models collapse, but also achieves good visual quality.
  arXiv  Detail & Related papers  (2021-07-20T01:55:21Z)
• Hidden Backdoor Attack against Semantic Segmentation Models [60.0327238844584]
  The emphbackdoor attack intends to embed hidden backdoors in deep neural networks (DNNs) by poisoning training data. We propose a novel attack paradigm, the emphfine-grained attack, where we treat the target label from the object-level instead of the image-level. Experiments show that the proposed methods can successfully attack semantic segmentation models by poisoning only a small proportion of training data.
  arXiv  Detail & Related papers  (2021-03-06T05:50:29Z)
• GreedyFool: Distortion-Aware Sparse Adversarial Attack [138.55076781355206]
  Modern deep neural networks (DNNs) are vulnerable to adversarial samples. Sparse adversarial samples can fool the target model by only perturbing a few pixels. We propose a novel two-stage distortion-aware greedy-based method dubbed as "GreedyFool"
  arXiv  Detail & Related papers  (2020-10-26T17:59:07Z)
• A Self-supervised Approach for Adversarial Robustness [105.88250594033053]
  Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems. This paper proposes a self-supervised adversarial training mechanism in the input space. It provides significant robustness against the textbfunseen adversarial attacks.
  arXiv  Detail & Related papers  (2020-06-08T20:42:39Z)

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.