conftrace_
← Learning Types
Machine Learning › Learning Types ›

Adversarial Learning

4,854 papers

Papers per year

Papers

Reconstruction Attack on Instance Encoding for Language Understanding EMNLP 2021
Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings EMNLP 2021
Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation EMNLP 2021
Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup EMNLP 2021
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning EMNLP 2021
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution EMNLP 2021
RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models EMNLP 2021
Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models EMNLP 2021
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization EMNLP 2021
Multi-granularity Textual Adversarial Attack with Behavior Cloning EMNLP 2021
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer EMNLP 2021
Adversarial Attack against Cross-lingual Knowledge Graph Alignment EMNLP 2021
Crosslingual Transfer Learning for Relation and Event Extraction via Word Category and Class Alignments EMNLP 2021
Gradient-based Adversarial Attacks against Text Transformers EMNLP 2021
Sequential Randomized Smoothing for Adversarially Robust Speech Recognition EMNLP 2021
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach EMNLP 2021
Generative Context Pair Selection for Multi-hop Question Answering EMNLP 2021
Investigating Robustness of Dialog Models to Popular Figurative Language Constructs EMNLP 2021
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks EMNLP 2021
Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods EMNLP 2021
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification EMNLP 2021
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models EMNLP 2021
FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations EMNLP 2021
A Strong Baseline for Query Efficient Attacks in a Black Box Setting EMNLP 2021
Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation EMNLP 2021