On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective

by   Jindong Wang, et al.

ChatGPT is a recent chatbot service released by OpenAI and is receiving increasing attention over the past few months. While evaluations of various aspects of ChatGPT have been done, its robustness, i.e., the performance to unexpected inputs, is still unclear to the public. Robustness is of particular concern in responsible AI, especially for safety-critical applications. In this paper, we conduct a thorough evaluation of the robustness of ChatGPT from the adversarial and out-of-distribution (OOD) perspective. To do so, we employ the AdvGLUE and ANLI benchmarks to assess adversarial robustness and the Flipkart review and DDXPlus medical diagnosis datasets for OOD evaluation. We select several popular foundation models as baselines. Results show that ChatGPT shows consistent advantages on most adversarial and OOD classification and translation tasks. However, the absolute performance is far from perfection, which suggests that adversarial and OOD robustness remains a significant threat to foundation models. Moreover, ChatGPT shows astounding performance in understanding dialogue-related texts and we find that it tends to provide informal suggestions for medical tasks instead of definitive answers. Finally, we present in-depth discussions of possible research directions.


page 1

page 2

page 3

page 4


It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness

Adversarial examples are inputs to machine learning models that an attac...

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications

This tutorial aims to introduce the fundamentals of adversarial robustne...

Clustering Effect of (Linearized) Adversarial Robust Models

Adversarial robustness has received increasing attention along with the ...

On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices

Vulnerability to adversarial attacks is a well-known weakness of Deep Ne...

RobustBench: a standardized adversarial robustness benchmark

Evaluation of adversarial robustness is often error-prone leading to ove...

Evaluating robustness of support vector machines with the Lagrangian dual approach

Adversarial examples bring a considerable security threat to support vec...

Please sign up or login with your details

Forgot password? Click here to reset