"Prompt injection attacks pose a serious threat to anyone who uses AI tools, but especially to professionals who rely on them at work. By exploiting a vulnerability that affects most AIs, a hacker can insert malicious code into a text prompt, which may then alter the results or even steal confidential data. Also: 5 custom ChatGPT instructions I use to get better AI results - faster Now, OpenAI has introduced a feature called Lockdown Mode to better thwart these types of attacks."
"OpenAI Lockdown Mode enhances the protection against prompt injections and other advanced threats. With this setting enabled, ChatGPT is limited in the ways it can interact with external systems and data, thereby restricting an attacker's ability to exfiltrate sensitive files. An optional security setting, Lockdown Mode isn't necessary for most ChatGPT users, OpenAI said in a news release on Friday."
Prompt injection attacks can insert malicious instructions into text prompts, enabling attackers to alter AI outputs or steal confidential data. These attacks present elevated risk for professionals who use AI in work contexts. Lockdown Mode limits ChatGPT's ability to interact with external systems and connected apps, reducing the chance that sensitive files or conversation data can be exfiltrated. Lockdown Mode is an optional, security-focused setting intended for executives, security professionals, and other high-risk users. The feature is available for specialized ChatGPT plans including Enterprise, Edu, Healthcare, and Teacher deployments. Elevated Risk labels warn of potentially risky AI tools and content.
Read at ZDNET
Unable to calculate read time
Collection
[
|
...
]