paper-with-me

Papers

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters

2025-01-23 · Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Sahand Ghorbanpour, Avisek Naug, Ricardo Luna Gutierrez, Antonio Guillen

We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Learning agent to add minimum distortion to input images while still causing misclassification by the target model. The agent uses a novel dual-action method to explore the input image at each step to identify sensitive regions for adding distortions while removing noises that have less impact on the target model. This dual action leads to faster and more efficient convergence of the attack. The platform can also be used to measure the robustness of image classification models against specific distortion types. Also, retraining the model with adversarial samples significantly improved robustness when evaluated on benchmark datasets. The proposed platform outperforms state-of-the-art methods in terms of the average number of queries required to cause misclassification. This advances trustworthiness with a positive social impact.

📄 PDF Abstract BibTeX arXiv:2501.14122

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classificationreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Ensemble Diversity Facilitates Adversarial Transferability

2024-01-01 · CVPR 2024 1 · Bowen Tang, Zheng Wang, Yi Bin, Qi Dou 외

With the advent of ensemble-based attacks the transferability of generated adversarial examples is elevated by a noticeable margin despite many methods only employing superficial integration yet ignoring the diversit…

Diversityreinforcement-learningReinforcement Learning

Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks

2020-06-24 · Huiying Li, Shawn Shan, Emily Wenger, Jiayun Zhang 외

Deep learning systems are known to be vulnerable to adversarial examples. In particular, query-based black-box attacks do not require knowledge of the deep learning model, but can compute adversarial examples over the ne…

image-classificationImage Classificationtext-classificationText Classification

Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information

2021-10-19 · Baolin Zheng, Peipei Jiang, Qian Wang, Qi Li 외

Adversarial attacks against commercial black-box speech platforms, including cloud speech APIs and voice control devices, have received little attention until recent years. The current "black-box" attacks all heavily rel…

Adversarial Attackglobal-optimizationSpeaker Recognition

Adversarial joint attacks on legged robots

2022-05-20 · Takuto Otomo, Hiroshi Kera, Kazuhiko Kawamoto

We address adversarial attacks on the actuators at the joints of legged robots trained by deep reinforcement learning. The vulnerability to the joint attacks can significantly impact the safety and robustness of legged r…

Deep Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement Learning+1

Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning

2022-11-15 · Yiran Huang, Yexu Zhou, Michael Hefenbrock, Till Riedel 외

The vulnerability of the high-performance machine learning models implies a security risk in applications with real-world consequences. Research on adversarial attacks is beneficial in guiding the development of machine …

Adversarial Attackreinforcement-learningReinforcement LearningReinforcement Learning (RL)