mlsanityData to 14 Oct 2026

Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack

arXiv 2411.12071 ↗First posted 18 Nov 2024cs.LG cs.CRcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

Adversarial examples represent a serious issue for the application of machine learning models in many sensitive domains. For generating adversarial examples, decision based black-box attacks are one of the most practical techniques as they only require query access to the model. One of the most recently proposed state-of-the-art decision based black-box attacks is Triangle Attack (TA). In this paper, we offer a high-level description of TA and explain potential theoretical limitations. We then propose a new decision based black-box attack, Triangle Attack with Reinforcement Learning (TARL). Our new attack addresses the limits of TA by leveraging reinforcement learning. This creates an attack that can achieve similar, if not better, attack accuracy than TA with half as many queries on state-of-the-art classifiers and defenses across ImageNet and CIFAR-10.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 42 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

10 of 42 references.

References · 10

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  7. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  8. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 120
  9. 2021Boosting Adversarial Transferability through Enhanced Momentumcited by 54
  10. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 24

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision
  2. 2025Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
  3. 2024Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
  4. 2025Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification
  5. 2025SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
  6. 2026Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization
  7. 2025Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
  8. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective