Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userContextualized Perturbation for Textual Adversarial Attack
اضطراب السياق لهجوم الخصم النصي
359
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعرض أمثلة الخصومة نقاط الضعف في نماذج معالجة اللغة الطبيعية (NLP)، ويمكن استخدامها لتقييم وتحسين متواضتهم. عادة ما تكون التقنيات الحالية لتوليد هذه الأمثلة تحركها القواعد المتخذة المحلية غير الملأمة في السياق، وغالبا ما تؤدي إلى مخرجات غير طبيعية وغير طبيعية. تقدم هذه الورقة كلير، وهو نموذج توليد مثال لمصدري محوري ينتج مخرجات بطلاقة وحكومية من خلال إجراءات قناع ثم تسلل. بناء Clare على نموذج لغة ملثم مسبقا مسبقا وتعديل المدخلات بطريقة تدرك السياق. نقترح ثلاث اضطرابات سياق، واستبدال وإدراج ودمج، والتي تسمح بتوليد مخرجات أطوال متنوعة. يمكن أن تجمع كلير بمرونة هذه الاضطرابات وتطبيقها في أي موقف في المدخلات، وبالتالي فهي قادرة على مهاجمة نموذج الضحية بشكل أكثر فعالية مع تعديلات أقل. توضح التجارب الواسعة والتقييم البشري أن كلير تتفوق على خطوط الأساس من حيث معدل النجاح الهجوم، والتشابه النصي والطلاقة والنحوية.
Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of generating such examples are typically driven by local heuristic rules that are agnostic to the context, often resulting in unnatural and ungrammatical outputs. This paper presents CLARE, a ContextuaLized AdversaRial Example generation model that produces fluent and grammatical outputs through a mask-then-infill procedure. CLARE builds on a pre-trained masked language model and modifies the inputs in a context-aware manner. We propose three contextualized perturbations, Replace, Insert and Merge, that allow for generating outputs of varied lengths. CLARE can flexibly combine these perturbations and apply them at any position in the inputs, and is thus able to attack the victim model more effectively with fewer edits. Extensive experiments and human evaluation demonstrate that CLARE outperforms the baselines in terms of attack success rate, textual similarity, fluency and grammaticality.
References used
https://aclanthology.org/
rate research
Read More
Recently, the textual adversarial attack models become increasingly popular due to their successful in estimating the robustness of NLP models. However, existing works have obvious deficiencies. (1)They usually consider only a single granularity of m
odification 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. To address such problems, in this paper 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. We conduct comprehensive experiments to evaluate our attack models by attacking BiLSTM, BERT and RoBERTa in two different black-box attack settings and three benchmark datasets. Experimental results show that our models achieve overall better attacking performance and produce more fluent and grammatical adversarial samples compared to baseline models. Besides, our adversarial attack agent significantly reduces the query times in both attack settings. Our codes are released at https://github.com/Yangyi-Chen/MAYA.
Representation learning is widely used in NLP for a vast range of tasks. However, representations derived from text corpora often reflect social biases. This phenomenon is pervasive and consistent across different neural models, causing serious conce
rn. Previous methods mostly rely on a pre-specified, user-provided direction or suffer from unstable training. In this paper, we propose an adversarial disentangled debiasing model to dynamically decouple social bias attributes from the intermediate representations trained on the main task. We aim to denoise bias information while training on the downstream task, rather than completely remove social bias and pursue static unbiased representations. Experiments show the effectiveness of our method, both on the effect of debiasing and the main task performance.
The robustness and security of natural language processing (NLP) models are significantly important in real-world applications. In the context of text classification tasks, adversarial examples can be designed by substituting words with synonyms unde
r certain semantic and syntactic constraints, such that a well-trained model will give a wrong prediction. Therefore, it is crucial to develop techniques to provide a rigorous and provable robustness guarantee against such attacks. In this paper, we propose WordDP to achieve certified robustness against word substitution at- tacks in text classification via differential privacy (DP). We establish the connection between DP and adversarial robustness for the first time in the text domain and propose a conceptual exponential mechanism-based algorithm to formally achieve the robustness. We further present a practical simulated exponential mechanism that has efficient inference with certified robustness. We not only provide a rigorous analytic derivation of the certified condition but also experimentally compare the utility of WordDP with existing defense algorithms. The results show that WordDP achieves higher accuracy and more than 30X efficiency improvement over the state-of-the-art certified robustness mechanism in typical text classification tasks.
We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding. The key idea is to introspect current mistakes and prioritize adversarial training steps to where the
model errs the most. Experiments show that TAT can significantly improve accuracy over standard adversarial training on GLUE and attain new state-of-the-art zero-shot results on XNLI. Our code will be released upon acceptance of the paper.
This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising conversation
al query reformulation and information retrieval modules. Despite its effectiveness, such a pipeline often includes multiple neural models that require long inference times. In addition, independently optimizing each module ignores dependencies among them. To address these shortcomings, we propose to integrate conversational query reformulation directly into a dense retrieval model. To aid in this goal, we create a dataset with pseudo-relevance labels for conversational search to overcome the lack of training data and to explore different training strategies. We demonstrate that our model effectively rewrites conversational queries as dense representations in conversational search and open-domain question answering datasets. Finally, after observing that our model learns to adjust the L2 norm of query token embeddings, we leverage this property for hybrid retrieval and to support error analysis.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
