2023
DOI: 10.48550/arxiv.2302.12095
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

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

Abstract: 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 Chat-GPT 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… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
29
0
2

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 25 publications
(31 citation statements)
references
References 34 publications
0
29
0
2
Order By: Relevance
“…These instances fall outside the range of the model's training data and present challenges to the model's performance and generalization ability. Some of the recent research works focused on evaluating the robustness of GLLMs to out-of-distribution instances [456], [461], adversarial prompts [458]- [460] and adversarial inputs [425], [455], [457], [462] in one or more natural language processing tasks. Table 21 presents a summary of research works assessing GLLMs robustness to out-of-distribution instances, adversarial prompts and adversarial inputs.…”
Section: Robustness Of Gllmsmentioning
confidence: 99%
See 3 more Smart Citations
“…These instances fall outside the range of the model's training data and present challenges to the model's performance and generalization ability. Some of the recent research works focused on evaluating the robustness of GLLMs to out-of-distribution instances [456], [461], adversarial prompts [458]- [460] and adversarial inputs [425], [455], [457], [462] in one or more natural language processing tasks. Table 21 presents a summary of research works assessing GLLMs robustness to out-of-distribution instances, adversarial prompts and adversarial inputs.…”
Section: Robustness Of Gllmsmentioning
confidence: 99%
“…Moreover, ChatGPT demonstrates better robustness to adversarial inputs than SOTA models in text-to-SQL generation. Some of the research works evaluated the GLLM robustness in multiple natural language understanding and generation tasks [455], [456], [458], [460]. Chen et al [455] assessed the robustness of GPT-3 and GPT-3.5 models on 21 datasets covering nine natural language understanding tasks.…”
Section: Robustness Of Gllmsmentioning
confidence: 99%
See 2 more Smart Citations
“…It has developed the ability to detect typical grammatical constructions and idioms after being trained on a vast corpus of text data, which includes books, papers, and websites [33]. This implies that even when the data it gets is not properly constructed or includes faults, it may nevertheless provide replies that are grammatically accurate and semantically relevant [34].…”
Section: E Natural Language Understandingmentioning
confidence: 99%