Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The long-lasting adversarial attack-and-defense arms race in Natural Language Processing (NLP) is algorithm-centric, providing valuable techniques for automatic robustness evaluation. However, the existing practice of robustness evaluation may exhibit issues of incomprehensive evaluation, impractical evaluation protocol, and invalid adversarial samples. In this paper, we aim to set up a unified automatic robustness evaluation framework, shifting towards model-centric evaluation to further exploit the advantages of adversarial attacks. To address the above challenges, we first determine robustness evaluation dimensions based on model capabilities and specify the reasonable algorithm to generate adversarial samples for each dimension. Then we establish the evaluation protocol, including evaluation settings and metrics, under realistic demands. Finally, we use the perturbation degree of adversarial samples to control the sample validity. We implement a toolkit RobTest that realizes our automatic robustness evaluation framework. In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework. The code will be made public at \url{https://github.com/thunlp/RobTest}.
Pre-trained language models (PLMs) achieve remarkable performance on many downstream tasks, but may fail in giving reliable estimates of their predictive uncertainty. Given the lack of a comprehensive understanding of PLMs calibration, we take a close look into this new research problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training process? (2) How effective are existing calibration methods? For the first question, we conduct fine-grained control experiments to study the dynamic change in PLMs' calibration performance in training. We consider six factors as control variables, including dataset difficulty, available training samples, training steps, the number of tunable parameters, model scale, and pretraining. In experiments, we observe a consistent change in calibration performance across six factors. We find that PLMs don't learn to become calibrated in training, evidenced by the continual increase in confidence, no matter the predictions are correct or not. We highlight that our finding presents some contradiction with two established conclusions: (a) Larger PLMs are more calibrated; (b) Pretraining improves model calibration. Next, we study the effectiveness of existing calibration methods in mitigating the overconfidence issue, in both in-distribution and various out-of-distribution settings. Besides unlearnable calibration methods, we adapt two recently proposed learnable methods that directly collect data to train models to have reasonable confidence estimations. Also, we propose extended learnable methods based on existing ones to further improve or maintain PLMs calibration without sacrificing the original task performance. Experimental results show that learnable methods significantly reduce PLMs' confidence in wrong predictions, and our methods exhibit superior performance compared with previous methods.
Textual adversarial samples play important roles in multiple subfields of NLP research, including security, evaluation, explainability, and data augmentation. However, most work mixes all these roles, obscuring the problem definitions and research goals of the security role that aims to reveal the practical concerns of NLP models. In this paper, we rethink the research paradigm of textual adversarial samples in security scenarios. We discuss the deficiencies in previous work and propose our suggestions that the research on the Security-oriented adversarial NLP (SoadNLP) should: (1) evaluate their methods on security tasks to demonstrate the real-world concerns; (2) consider real-world attackers' goals, instead of developing impractical methods. To this end, we first collect, process, and release a security datasets collection Advbench. Then, we reformalize the task and adjust the emphasis on different goals in SoadNLP. Next, we propose a simple method based on heuristic rules that can easily fulfill the actual adversarial goals to simulate real-world attack methods. We conduct experiments on both the attack and the defense sides on Advbench. Experimental results show that our method has higher practical value, indicating that the research paradigm in SoadNLP may start from our new benchmark. All the code and data of Advbench can be obtained at \url{https://github.com/thunlp/Advbench}.
Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been proposed, it is of great significance to perform rigorous evaluations. However, we highlight two issues in previous backdoor learning evaluations: (1) The differences between real-world scenarios (e.g. releasing poisoned datasets or models) are neglected, and we argue that each scenario has its own constraints and concerns, thus requires specific evaluation protocols; (2) The evaluation metrics only consider whether the attacks could flip the models' predictions on poisoned samples and retain performances on benign samples, but ignore that poisoned samples should also be stealthy and semantic-preserving. To address these issues, we categorize existing works into three practical scenarios in which attackers release datasets, pre-trained models, and fine-tuned models respectively, then discuss their unique evaluation methodologies. On metrics, to completely evaluate poisoned samples, we use grammar error increase and perplexity difference for stealthiness, along with text similarity for validity. After formalizing the frameworks, we develop an open-source toolkit OpenBackdoor to foster the implementations and evaluations of textual backdoor learning. With this toolkit, we perform extensive experiments to benchmark attack and defense models under the suggested paradigm. To facilitate the underexplored defenses against poisoned datasets, we further propose CUBE, a simple yet strong clustering-based defense baseline. We hope that our frameworks and benchmarks could serve as the cornerstones for future model development and evaluations.
Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage, where model predictions can be misled by inserting certain triggers into the text. In this paper, we explore this universal vulnerability by either injecting backdoor triggers or searching for adversarial triggers on pre-trained language models using only plain text. In both scenarios, we demonstrate that our triggers can totally control or severely decrease the performance of prompt-based models fine-tuned on arbitrary downstream tasks, reflecting the universal vulnerability of the prompt-based learning paradigm. Further experiments show that adversarial triggers have good transferability among language models. We also find conventional fine-tuning models are not vulnerable to adversarial triggers constructed from pre-trained language models. We conclude by proposing a potential solution to mitigate our attack methods. Code and data are publicly available at https://github.com/leix28/prompt-universal-vulnerability
Despite great success on many machine learning tasks, deep neural networks are still vulnerable to adversarial samples. While gradient-based adversarial attack methods are well-explored in the field of computer vision, it is impractical to directly apply them in natural language processing due to the discrete nature of text. To bridge this gap, we propose a general framework to adapt existing gradient-based methods to craft textual adversarial samples. In this framework, gradient-based continuous perturbations are added to the embedding layer and are amplified in the forward propagation process. Then the final perturbed latent representations are decoded with a mask language model head to obtain potential adversarial samples. In this paper, we instantiate our framework with \textbf{T}extual \textbf{P}rojected \textbf{G}radient \textbf{D}escent (\textbf{TPGD}). We conduct comprehensive experiments to evaluate our framework by performing transfer black-box attacks on BERT, RoBERTa and ALBERT on three benchmark datasets. Experimental results demonstrate our method achieves an overall better performance and produces more fluent and grammatical adversarial samples compared to strong baseline methods. All the code and data will be made public.
Backdoor attacks are a kind of emergent security threat in deep learning. When a deep neural model is injected with a backdoor, it will behave normally on standard inputs but give adversary-specified predictions once the input contains specific backdoor triggers. Current textual backdoor attacks have poor attack performance in some tough situations. In this paper, we find two simple tricks that can make existing textual backdoor attacks much more harmful. The first trick is to add an extra training task to distinguish poisoned and clean data during the training of the victim model, and the second one is to use all the clean training data rather than remove the original clean data corresponding to the poisoned data. These two tricks are universally applicable to different attack models. We conduct experiments in three tough situations including clean data fine-tuning, low poisoning rate, and label-consistent attacks. Experimental results show that the two tricks can significantly improve attack performance. This paper exhibits the great potential harmfulness of backdoor attacks. All the code and data will be made public to facilitate further research.
Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to most NLP tasks, and thus suitable for adversarial and backdoor attacks. In this paper, we make the first attempt to conduct adversarial and backdoor attacks based on text style transfer, which is aimed at altering the style of a sentence while preserving its meaning. We design an adversarial attack method and a backdoor attack method, and conduct extensive experiments to evaluate them. Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer -- the attack success rates can exceed 90% without much effort. It reflects the limited ability of NLP models to handle the feature of text style that has not been widely realized. In addition, the style transfer-based adversarial and backdoor attack methods show superiority to baselines in many aspects. All the code and data of this paper can be obtained at https://github.com/thunlp/StyleAttack.
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 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. 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.