22 |
Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation ...
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
25 |
Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings ...
|
|
|
|
BASE
|
|
Show details
|
|
28 |
Unsupervised Multi-View Post-OCR Error Correction With Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
29 |
AttentionRank: Unsupervised Keyphrase Extraction using Self and Cross Attentions ...
|
|
|
|
BASE
|
|
Show details
|
|
30 |
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Multi-granularity Textual Adversarial Attack with Behavior Cloning ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.371/ Abstract: Existing works have obvious deficiencies. (1) They usually consider only a single granularity of modification strategies (e.g. word-level or sentence-level), which is insufficient to explore the holistic textual space for generation; (2) They need to query victim models hundreds of times to make a successful attack, which is highly inefficient in practice. We propose MAYA, a Multi-grAnularitY Attack model to effectively generate high-quality adversarial samples with fewer queries to victim models. Furthermore, we propose a reinforcement-learning based method to train a multi-granularity attack agent through behavior cloning with the expert knowledge from our MAYA algorithm to further reduce the query times. Additionally, we also adapt the agent to attack black-box models that only output labels without confidence scores. ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
|
|
URL: https://underline.io/lecture/37485-multi-granularity-textual-adversarial-attack-with-behavior-cloning https://dx.doi.org/10.48448/xy82-2s58
|
|
BASE
|
|
Hide details
|
|
32 |
Automatic Fact-Checking with Document-level Annotations using BERT and Multiple Instance Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
33 |
Towards the Early Detection of Child Predators in Chat Rooms: A BERT-based Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
34 |
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
35 |
WebSRC: A Dataset for Web-Based Structural Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
36 |
Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
Semantic Categorization of Social Knowledge for Commonsense Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
38 |
Pre-train or Annotate? Domain Adaptation with a Constrained Budget ...
|
|
|
|
BASE
|
|
Show details
|
|
40 |
Learning with Different Amounts of Annotation: From Zero to Many Labels ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|