No article text was recorded for this version.
iterative decision boundary linearization
Version 1 of 173 papers82 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
- Blog: Generating Natural Language Attacks in a Hard Label Black Box Setting
- Blog: Near-Optimal Evasion of Convex-Inducing Classifiers
- Blog: Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
- Blog: Detection of Iterative Adversarial Attacks via Counter Attack
- Blog: Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework
- Blog: Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
- Blog: The LogBarrier Adversarial Attack: Making Effective Use of Decision Boundary Information
- Blog: Multi-bit, Black-box Watermarking of Deep Neural Networks in Embedded Applications
- Blog: Research on the robustness of the open-world test-time training model
- Blog: MFABA: A More Faithful and Accelerated Boundary-Based Attribution Method for Deep Neural Networks
- Blog: Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
- Blog: HopSkipJumpAttack: A Query-Efficient Decision-Based Attack
- Blog: Promoting Counterfactual Robustness through Diversity
- Blog: c-MBA: Adversarial Attack for Cooperative MARL Using Learned Dynamics Model
- Blog: Character As Pixels: A Controllable Prompt Adversarial Attacking Framework for Black-Box Text Guided Image Generation Models
- Blog: SeRI: Gradient-Free Sensitive Region Identification in Decision-Based Black-Box Attacks
- Blog: Black-Box Boundary Attack Based on Gradient Optimization
- Blog: Curls & Whey: Boosting Black-Box Adversarial Attacks
- Blog: Actionable Model-Centric Explanations (Student Abstract)
- Blog: Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
- Blog: Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
- Blog: GeoDA: A Geometric Framework for Black-Box Adversarial Attacks
- Blog: GSBA$^K$: $top$-$K$ Geometric Score-based Black-box Attack
- Blog: Sign-OPT: A Query-Efficient Hard-label Adversarial Attack
- Blog: HARE: Human-in-the-Loop Algorithmic Recourse
- Blog: Multi-label Adversarial Perturbations
- Blog: Auditing and Debugging Deep Learning Models via Flip Points: Individual-Level and Group-Level Analysis
- Blog: Understanding Catastrophic Overfitting in Single-step Adversarial Training
- Blog: A Distributed Biased Boundary Attack Method in Black-Box Attack
- Blog: Polishing Decision-Based Adversarial Noise With a Customized Sampling
- Blog: A Deep Dive into Adversarial Robustness in Zero-Shot Learning
- Blog: Triangle Attack: A Query-Efficient Decision-Based Adversarial Attack
- Blog: SparseFool: A Few Pixels Make a Big Difference
- Blog: Hard-Label Based Small Query Black-Box Adversarial Attack
- Blog: An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack
- Blog: Second-Order Provable Defenses against Adversarial Attacks
- Blog: Max-Margin Adversarial (MMA) Training: Direct Input Space Margin Maximization through Adversarial Training
- Blog: Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
- Blog: Boundary Attack++: Query-Efficient Decision-Based Adversarial Attack
- Blog: Using adaptive learning rate to generate adversarial images
- Blog: Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks
- Blog: ADef: an Iterative Algorithm to Construct Adversarial Deformations
- Blog: Adversarial Examples versus Cloud-Based Detectors: A Black-Box Empirical Study
- Blog: Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
- Blog: Robustness for Non-Parametric Classification: A Generic Attack and Defense
- Blog: A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
- Blog: GreedyPixel: Fine-Grained Black-Box Adversarial Attack via Greedy Algorithm
- Blog: SparseFool: a few pixels make a big difference
- Blog: Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation
- Blog: Hear "No Evil", See "Kenansville": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systems
- Blog: Robust Models Are More Interpretable Because Attributions Look Normal
- Blog: Adversarial Framing for Image and Video Classification
- Blog: Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach
- Blog: Minimum Power Adversarial Attacks in Communication Signal Modulation Classification with Deep Learning
- Blog: DeepFool: a simple and accurate method to fool deep neural networks
- Blog: BASAR: Black-Box Attack on Skeletal Action Recognition
- Blog: Borderline Sample Extraction from a Trained Classifier
- Blog: TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data
- Blog: 3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack
Showing 60 of 73 papers.
History & citation
Current · Permanent link
- Geometric Boundary Search for Query-Efficient Black-Box Attacks merged into this direction (75% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_iterative_decision_boundary_linearizatio_ccb5102d,
title = {iterative decision boundary linearization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/iterative-decision-boundary-linearization/rdr_ccb5102d627547c1b6731cb5a4cdfad5},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_iterative_decision_boundary_linearizatio_ccb5102d_v1,
title = {iterative decision boundary linearization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/iterative-decision-boundary-linearization/rdr_ccb5102d627547c1b6731cb5a4cdfad5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}