Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRed Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks
62
0
0.0
(
0
)
Added by
Zhengyan Zhang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Pre-trained models (PTMs) have been widely used in various downstream tasks. The parameters of PTMs are distributed on the Internet and may suffer backdoor attacks. In this work, we demonstrate the universal vulnerability of PTMs, where fine-tuned PTMs can be easily controlled by backdoor attacks in arbitrary downstream tasks. Specifically, attackers can add a simple pre-training task, which restricts the output representations of trigger instances to pre-defined vectors, namely neuron-level backdoor attack (NeuBA). If the backdoor functionality is not eliminated during fine-tuning, the triggers can make the fine-tuned model predict fixed labels by pre-defined vectors. In the experiments of both natural language processing (NLP) and computer vision (CV), we show that NeuBA absolutely controls the predictions for trigger instances without any knowledge of downstream tasks. Finally, we apply several defense methods to NeuBA and find that model pruning is a promising direction to resist NeuBA by excluding backdoored neurons. Our findings sound a red alarm for the wide use of PTMs. Our source code and models are available at url{https://github.com/thunlp/NeuBA}.
rate research
Read More
textbf{P}re-textbf{T}rained textbf{M}odeltextbf{s} have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be maliciously poisoned with certain triggers. When the triggers are activated, even the fine-tuned model will predict pre-defined labels, causing a security threat. These backdoors generated by the poisoning methods can be erased by changing hyper-parameters during fine-tuning or detected by finding the triggers. In this paper, we propose a stronger weight-poisoning attack method that introduces a layerwise weight poisoning strategy to plant deeper backdoors; we also introduce a combinatorial trigger that cannot be easily detected. The experiments on text classification tasks show that previous defense methods cannot resist our weight-poisoning method, which indicates that our method can be widely applied and may provide hints for future model robustness studies.
Integrating visual features has been proved useful for natural language understanding tasks. Nevertheless, in most existing multimodal language models, the alignment of visual and textual data is expensive. In this paper, we propose a novel semi-supervised visual integration framework for pre-trained language models. In the framework, the visual features are obtained through a visualization and fusion mechanism. The uniqueness includes: 1) the integration is conducted via a semi-supervised approach, which does not require aligned images for every sentences 2) the visual features are integrated as an external component and can be directly used by pre-trained language models. To verify the efficacy of the proposed framework, we conduct the experiments on both natural language inference and reading comprehension tasks. The results demonstrate that our mechanism brings improvement to two strong baseline models. Considering that our framework only requires an image database, and no not requires further alignments, it provides an efficient and feasible way for multimodal language learning.
Public security vulnerability reports (e.g., CVE reports) play an important role in the maintenance of computer and network systems. Security companies and administrators rely on information from these reports to prioritize tasks on developing and deploying patches to their customers. Since these reports are unstructured texts, automatic information extraction (IE) can help scale up the processing by converting the unstructured reports to structured forms, e.g., software names a
Recent explorations of large-scale pre-trained language models (PLMs) such as GPT-3 have revealed the power of PLMs with huge amounts of parameters, setting off a wave of training ever-larger PLMs. However, training a large-scale PLM requires tremendous amounts of computational resources, which is time-consuming and expensive. In addition, existing large-scale PLMs are mainly trained from scratch individually, ignoring the availability of many existing well-trained PLMs. To this end, we explore the question that how can previously trained PLMs benefit training larger PLMs in future. Specifically, we introduce a novel pre-training framework named knowledge inheritance (KI), which combines both self-learning and teacher-guided learning to efficiently train larger PLMs. Sufficient experimental results demonstrate the feasibility of our KI framework. We also conduct empirical analyses to explore the effects of teacher PLMs pre-training settings, including model architecture, pre-training data, etc. Finally, we show that KI can well support lifelong learning and knowledge transfer.
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words in pre-training could further improve the performance of PrLMs. However, given that span-level clues are introduced and fixed in pre-training, previous methods are time-consuming and lack of flexibility. To alleviate the inconvenience, this paper presents a novel span fine-tuning method for PrLMs, which facilitates the span setting to be adaptively determined by specific downstream tasks during the fine-tuning phase. In detail, any sentences processed by the PrLM will be segmented into multiple spans according to a pre-sampled dictionary. Then the segmentation information will be sent through a hierarchical CNN module together with the representation outputs of the PrLM and ultimately generate a span-enhanced representation. Experiments on GLUE benchmark show that the proposed span fine-tuning method significantly enhances the PrLM, and at the same time, offer more flexibility in an efficient way.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
