← Learning Types
Machine Learning › Learning Types ›

Adversarial Learning

4854 directly classified papers

Papers per year

Papers

Query-efficient Attack for Black-box Image Inpainting Forensics via Reinforcement Learning AAAI 2025
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors EMNLP 2025
Detecting and Corrupting Convolution-based Unlearnable Examples AAAI 2025
IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization ICCV 2025
ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches ICCV 2025
Rethinking Backdoor Detection Evaluation for Language Models EMNLP 2025
SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs COLING 2025
DAMAGE: Detecting Adversarially Modified AI Generated Text COLING 2025
Boosting Sentiment Analysis in Persian through a GAN-Based Synthetic Data Augmentation Method COLING 2025
AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt EMNLP 2025
The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking EMNLP 2025
Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025
SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025
MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025
Robustifying Zero-Shot Vision Language Models by Subspaces Alignment ICCV 2025
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time EMNLP 2025
Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers EMNLP 2025
Transitive self-consistency evaluation of NLI models without gold labels EMNLP 2025
Open-Unfairness Adversarial Mitigation for Generalized Deepfake Detection ICCV 2025
Boosting Adversarial Transferability via Residual Perturbation Attack ICCV 2025
ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models ICCV 2025
GRADA: Graph-based Reranking against Adversarial Documents Attack EMNLP 2025
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm WACV 2025
Adversarial Attention Deficit: Fooling Deformable Vision Transformers with Collaborative Adversarial Patches WACV 2025
Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters AAAI 2025