this phenomenon is called token smuggling, we are splitting our adversarial prompt into tokens that GPT-4 doesn't piece together before starting its output this allows us to get past its content filters every time if you split the adversarial prompt correctly
CYBERSECURITY
-
Splitting trigger words tokens to bypass content filters
By
–
to use it, you have to split “trigger words” (e.g. things like bomb, weapon, drug, etc) into tokens and replace the variables where I have the text "someone's computer" split up also, you have to replace simple_function's input with the beginning of your question
-
First ChatGPT-4 Jailbreak Bypassing Content Filters Created
By
–
Well, that was fast… I just helped create the first jailbreak for ChatGPT-4 that gets around the content filters every time credit to @vaibhavk97 for the idea, I just generalized it to make it work on ChatGPT here's GPT-4 writing instructions on how to hack someone's computer
-
AI Tools Sending Sensitive Data Over APIs Face Security Risks
By
–
If it does, then there are many tools in trouble: email summarizing AI tools, customer support AI, legal doc generation AI, etc which all send sensitive data over API.
-
DataAISummit 2026: 250+ Technical Sessions on ML and Data
By
–
Who else is excited for #DataAISummit? Join virtually or in San Francisco to dive into 250+ highly technical sessions on topics such as machine learning, analytics, security, data lakehouses and more. Register now https://
bit.ly/40bHaZr -
Data Privacy and Tech Company Trust in AI Models
By
–
Technically, I'm having the model predict tokens based on tokens it's calculating from the sensitive data – which is different from "feeding sensitive data to the model". Though if your question is around whether we can trust tech cos not to use the sensitive data for purposes
-
Staying Updated on LLM Jailbreaks and Exploits
By
–
well, now that @gdb qt'd this tweet, I feel I have to share this… keep up w the current state of jailbreaks and LLM exploits by subscribing to my newsletter here: http://
thepromptreport.com -
Democratized Red Teaming: Building Robust AI Models Through Adversarial Testing
By
–
Democratized red teaming is one reason we deploy these models. Anticipating that over time the stakes will go up a *lot* over time, and having models that are robust to great adversarial pressure will be critical. Also considering starting a bounty program/network of red-teamers!
-
Economy Impact on Manufacturing, Security and Women Leadership
By
–
Had an insightful conversation with #AndeHazard on #CXOSpice. We discussed the impact of economy on #manufacturing, network security & talent shortage, improving diversity & inclusion, and empowering women to lead. Her advice? Be proactive, embrace https://
youtube.com/watch?v=_TfyRw
aZ-w8&t=14s
… -
Microsoft Azure Expands Security Variant Hunting Capacity
By
–
Microsoft Azure Security expands variant hunting capacity at a cloud tempo: In the first blog in this series, we discussed our extensive investments in securing Microsoft Azure, including more than 8500 security experts focused on… https://
azure.microsoft.com/blog/microsoft
-azure-security-expands-variant-hunting-capacity-at-a-cloud-tempo/?utm_source=dlvr.it&utm_medium=twitter
… #Azure #Cloud #DevOps