Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBe Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
كن حذرا حول تضييق كلمة تسمم: استكشاف ضعف طبقات التضمين في نماذج NLP
249
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
كشفت الدراسات الحديثة عن تهديد أمني لنماذج معالجة اللغة الطبيعية (NLP)، تسمى هجوم الوكيل. يمكن أن تحافظ نماذج الضحايا الحفاظ على أداء تنافسي على عينات نظيفة أثناء التصرف بشكل غير واضح على العينات ذات كلمة مشغلة محددة إدراجها. عادة ما تتحمل أساليب المهاجمة السابقة أن المهاجمين لديهم درجة معينة من المعرفة بالبيانات، إما مجموعة البيانات التي يستخدمها المستخدمون أو مجموعات البيانات الوكيل لمهمة مماثلة، لتنفيذ إجراء تسمم البيانات. ومع ذلك، في هذه الورقة، نجد أنه من الممكن اختراق النموذج بطريقة خالية من البيانات عن طريق تعديل ناقلات كلمة واحدة تضمينها، مع عدم التضحية بدقة تقريبا على عينات نظيفة. تظهر النتائج التجريبية على تحليل المعنويات ومهام تصنيف زوج الجملة أن طريقتنا أكثر كفاءة وسيلة كريهة. نأمل أن يرفع هذا العمل الوعي بمثل هذا المخاطر الأمنية الحرجة المخفية في طبقات تضمين نماذج NLP. يتوفر الكود الخاص بنا في https://github.com/lancopku/mbedding-poisioning.
Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific trigger word inserted. Previous backdoor attacking methods usually assume that attackers have a certain degree of data knowledge, either the dataset which users would use or proxy datasets for a similar task, for implementing the data poisoning procedure. However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples. Experimental results on sentiment analysis and sentence-pair classification tasks show that our method is more efficient and stealthier. We hope this work can raise the awareness of such a critical security risk hidden in the embedding layers of NLP models. Our code is available at https://github.com/lancopku/Embedding-Poisoning.
References used
https://aclanthology.org/
rate research
Read More
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we develop a new da
ta poisoning attack that allows an adversary to control model predictions whenever a desired trigger phrase is present in the input. For instance, we insert 50 poison examples into a sentiment model's training set that causes the model to frequently predict Positive whenever the input contains James Bond''. Crucially, we craft these poison examples using a gradient-based procedure so that they do not mention the trigger phrase. We also apply our poison attack to language modeling (Apple iPhone'' triggers negative generations) and machine translation (iced coffee'' mistranslated as hot coffee''). We conclude by proposing three defenses that can mitigate our attack at some cost in prediction accuracy or extra human annotation.
The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the compression o
f these models to improve their inference time and memory footprint. This paper presents a novel loss objective to compress token embeddings in the Transformer-based models by leveraging an AutoEncoder architecture. More specifically, we emphasize the importance of the direction of compressed embeddings with respect to original uncompressed embeddings. The proposed method is task-agnostic and does not require further language modeling pre-training. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity. Moreover, we evaluate our proposed approach over SQuAD v1.1 dataset and several downstream tasks from the GLUE benchmark, where we also outperform the baseline in most scenarios. Our code is public.
The problem of designing NLP solvers for math word problems (MWP) has seen sustained research activity and steady gains in the test accuracy. Since existing solvers achieve high performance on the benchmark datasets for elementary level MWPs containi
ng one-unknown arithmetic word problems, such problems are often considered solved'' with the bulk of research attention moving to more complex MWPs. In this paper, we restrict our attention to English MWPs taught in grades four and lower. We provide strong evidence that the existing MWP solvers rely on shallow heuristics to achieve high performance on the benchmark datasets. To this end, we show that MWP solvers that do not have access to the question asked in the MWP can still solve a large fraction of MWPs. Similarly, models that treat MWPs as bag-of-words can also achieve surprisingly high accuracy. Further, we introduce a challenge dataset, SVAMP, created by applying carefully chosen variations over examples sampled from existing datasets. The best accuracy achieved by state-of-the-art models is substantially lower on SVAMP, thus showing that much remains to be done even for the simplest of the MWPs.
Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only composed of
the multi-head attention; other components can also contribute to Transformers' progressive performance. In this study, we extended the scope of the analysis of Transformers from solely the attention patterns to the whole attention block, i.e., multi-head attention, residual connection, and layer normalization. Our analysis of Transformer-based masked language models shows that the token-to-token interaction performed via attention has less impact on the intermediate representations than previously assumed. These results provide new intuitive explanations of existing reports; for example, discarding the learned attention patterns tends not to adversely affect the performance. The codes of our experiments are publicly available.
Natural language understanding is an important task in modern dialogue systems. It becomes more important with the rapid extension of the dialogue systems' functionality. In this work, we present an approach to zero-shot transfer learning for the tas
ks of intent classification and slot-filling based on pre-trained language models. We use deep contextualized models feeding them with utterances and natural language descriptions of user intents to get text embeddings. These embeddings then used by a small neural network to produce predictions for intent and slot probabilities. This architecture achieves new state-of-the-art results in two zero-shot scenarios. One is a single language new skill adaptation and another one is a cross-lingual adaptation.
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
