GPT-3-Based Twitter Bot Hijacked Using Prompt Injection Attacks
Description
Remoteli.io's GPT-3-based Twitter bot was shown being hijacked by Twitter users who redirected it to repeat or generate any phrases.
Actors
Alleged Deployers
- stephan-de-vries
Alleged Developers
- openai
- stephan-de-vries
Harmed Parties
- stephan-de-vries
Classification
Risk Domain
Privacy & SecurityRisk Subdomain
2.2. AI system security vulnerabilities and attacks
MIT Risk Profile
Topics
Source
Related Incidents (Privacy & Security)
View all →Research Papers on This Topic
View all →StarCoder: may the source be with you!
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
LineVD: Statement-level Vulnerability Detection using Graph Neural Networks
TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Mitigation Tools
Tools related to this risk domain, via shared responsible AI topics.
Open Source
View all →flair
flairNLP/flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
⭐ 14,353
PySyft
OpenMined/PySyft
Perform data science on data that remains in someone else's server
⭐ 10,041
FATE
FederatedAI/FATE
An Industrial Grade Federated Learning Framework
⭐ 6,100
adversarial-robustness-toolbox