← Learning Types

Machine Learning › Learning Types ›

Adversarial Learning

4854 directly classified papers

Papers per year

Papers

Unnoticed Yet Effective: A Hybrid Physical Camouflage Framework Against DNNs and Human Perception AAAI 2026

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs AAAI 2026

Good Gradients Poison Your Model: Evading Defenses in Federated Learning via Boundary-adaptive Perturbation AAAI 2026

Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion AAAI 2026

VBF++: Variational Bayesian Fusion with Context-Aware Priors and Recommendation-Guided Adversarial Refinement for Multimodal Video Recommendation AAAI 2026

Multi-granularity Intent Modeling with Adversarial Robustness for Sequential Recommendation AAAI 2026

DRFGD: Disentangled Representation-Focused Generative Defense for Attack-Tolerant Cross-Modal Hashing AAAI 2026

Poisoning with a Pill: Circumventing Detection in Federated Learning AAAI 2026

Robust Decentralized Multi-armed Bandits: From Corruption-Resilience to Byzantine-Resilience AAAI 2026

FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training AAAI 2026

Learning Fair Representations with Kolmogorov-Arnold Networks AAAI 2026

Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning AAAI 2026

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

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026

Patch Your Matcher: Correspondence-Aware Image-to-Image Translation Unlocks Cross-Modal Matching via Single-Modality Priors WACV 2026

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

Lose Your Self (LoYS): An Adversarial Entropy-based Unsupervised Approach for Model Debiasing WACV 2026

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

Cluster-Guided Adversarial Perturbations for Robust Contrastive Learning WACV 2026

MageBench: Bridging Large Multimodal Models to Agents WACV 2026

ToxiPrompt: A Two-Stage Red-Teaming Approach for Balancing Adversarial Prompt Diversity and Response Toxicity EACL 2026

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

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models EACL 2026

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

Vulnerability-Aware Robust Multimodal Adversarial Training AAAI 2026