Extracting Training Data from ChatGPT
I’m wondering if OpenAI requested a CVE for the disclosure of this vulnerability.
#llm #llms #openai #vulnerability #chatgpt
🔗 https://not-just-memorization.github.io/extracting-training-data-from-chatgpt.html
Extracting Training Data from ChatGPT
I’m wondering if OpenAI requested a CVE for the disclosure of this vulnerability.
#llm #llms #openai #vulnerability #chatgpt
🔗 https://not-just-memorization.github.io/extracting-training-data-from-chatgpt.html
Digging a little bit in the some ICC profiles added in signal-app, I updated the original issue and there is clearly an issue where new ICC profiles are created from the Google skia library.
https://github.com/signalapp/Signal-Desktop/issues/6031#issuecomment-1702432836
This issue only appears when the media-quality is to high. Maybe an allow-list strategy like the mat2 tool written by @jvoisin would be better to be sure that new metadata created are discarded by default.
Enjoy when humans are using machines in unexpected ways. I break stuff and I do stuff.The other side is at @a (photography and art)#infosec #opensource #threatintelligence #fedi22
GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.
All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.