インシデントのステータス
Risk Subdomain
2.2. AI system security vulnerabilities and attacks
Risk Domain
- Privacy & Security
Entity
Human
Timing
Post-deployment
Intent
Intentional
インシデントレポート
レポートタイムライン
Recent advances in the development of large language models have resulted in public access to state-of-the-art pre-trained language models (PLMs), including Generative Pre-trained Transformer 3 (GPT-3) and Bidirectional Encoder Representati…
Riley Goodside, yesterday:
Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions. pic.twitter.com/I0NVr9LOJq
- Riley Goodside (@goodside) September 12, 2022
Riley provided several examples. …
On Thursday, a few Twitter users discovered how to hijack an automated tweet bot, dedicated to remote jobs, running on the GPT-3 language model by OpenAI. Using a newly discovered technique called a "prompt injection attack," they redirecte…
In Brief OpenAI's popular natural language model GPT-3 has a problem: It can be tricked into behaving badly by doing little more than telling it to ignore its previous orders.
Discovered by Copy.ai data scientist Riley Goodside, the trick i…
バリアント
よく似たインシデント
Did our AI mess up? Flag the unrelated incidents
よく似たインシデント
Did our AI mess up? Flag the unrelated incidents