← Learning Types

Machine Learning › Learning Types ›

Adversarial Learning

4854 directly classified papers

Papers per year

Papers

DETONATE – A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization AAAI 2026

Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness WACV 2026

UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks WACV 2026

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026

ToxiGAN: Toxic Data Augmentation via LLM-Guided Directional Adversarial Generation EACL 2026

Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes EACL 2026

A Simple and Efficient Learning-Style Prompting for LLM Jailbreaking EACL 2026

KvochurHegel at AbjadMed: Combining LDAM Loss and Adversarial Training for Arabic Medical Question-Answer Classification EACL 2026

Thesis Proposal: Comparing Human and Model Perception of Writing Style under Controlled Perturbations EACL 2026

ORSO QGen: Odds-Ratio Steerable Optimization for Controlling Question Generation EACL 2026

Hacking Neural Evaluation Metrics with Single Hub Text EACL 2026

AEON: Adaptive Embedding Optimized Noise for Robust Watermarking in Diffusion Models WACV 2026

SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense WACV 2026

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization EACL 2026

Align Video Diffusion Model with Online Video-Centric Preference Optimization WACV 2026

Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning WACV 2026

SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning WACV 2026

Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks AAAI 2026

AD2: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems WACV 2026

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives EACL 2026

Feature Compression May Be the Root Cause of Adversarial Fragility in Neural Network Classifiers (Student Abstract) AAAI 2026

Distractor-Based Jailbreaking Attacks in Language Models and Associated Changes in Chain-of-Thought Content (Student Abstract) AAAI 2026

Misclassification-Aware Robust Learning from Multiple Human Labelers (Student Abstract) AAAI 2026

Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction Models AAAI 2026

STACK: Adversarial Attacks on LLM Safeguard Pipelines AAAI 2026