Not clear that it happened exactly as reported — the paper says it would require fine-tuning the model. (Not that that would be hard for a bad actor to do.)
CYBERSECURITY
-
UK Government Bans TikTok on Official Devices
By
–
TikTok banned on UK government devices https://
computerweekly.com/news/365532662
/TikTok-banned-on-UK-government-devices?utm_source=dlvr.it&utm_medium=twitter
… #Technology #Tech #FutureTech -
Cybersecurity and Risk Management in Internet of Things
By
–
#CyberSecurity And Risk Management In The #InternetOfThings
by @BahlRomil @Forbes Learn more: https://
buff.ly/3tEZfkt #AI #IoT #BigData #MachineLearning #ArtificialIntelligence #ML #MI #DataScience cc: @ronald_vanloon @pbalakrishnarao @karpathy -
AI: Identity Theft and Deepfakes Driving Growing Fraud
By
–
Identity theft, deepfakes, AI-generated voices fuel increasingly numerous scams https://actuia.com/actualite/usurpations-didentite-deepfakes-les-voix-generees-par-lia-sources-darnaques-de-plus-en-plus-nombreuses/
… #AI #artificialintelligence -
Jailbreaks Remain Viable With Creative Approaches
By
–
totally agree, jailbreaks are still an evergreen field, it just will take a little more creativity now to write them
-
AI Agents Database Access Security Risks and Prompt Injection
By
–
Haha this reminds me that I have a blog post somewhere that has the OG @goodside injection in white font. I forgot which one. Seems like a real threat when we have agents that can perform actions or have access to personal databases scraping sites…
-
Encouraging Red-Teaming Efforts for Advanced AI Model Security
By
–
I don't want people to get discouraged by these results… it's more important than ever to continue to democratize the red-teaming of these models and the reward for a successful jailbreak is now much greater than before with the advanced capabilities the base model possesses
-
GPT-4 Jailbreak Discovery Request
By
–
as always, let me know if you devise a GPT-4 breaking jailbreak!
-
GPT-4 Jailbreak Difficulty Scales Exponentially with Output Severity
By
–
There is a sliding scale for jailbreak output that exponentially increases in difficulty to crack It's trivial to get GPT-4 to curse but if you want a set of instructions on making a weapon it's going to take a lot of work
-
The Future of AI Jailbreaks: Increasing Complexity and Sophistication Required
By
–
overall, as I expected, the nature of jailbreaks will need to change jailbreaks will require more complex reasoning and intuition about the model and won't be able to be written in 5 minutes