Watermarking & Labelling tools to track and authenticate AI-generated content, ensuring traceability and security. Apply Now at https://
indiaai.gov.in/article/expres
sion-of-interest-for-safe-trusted-ai-projects-under-indiaai-mission
… @GoI_MeitY @abhish18 @_DigitalIndia #ResponsibleAI #Watermarking #SyntheticMedia #ContentSecurity
SECURITY
-
AI Watermarking Tools for Content Authentication and Traceability
By
–
-
Hugging Face X Account Compromised Security Incident
By
–
The Hugging Face account on X/Twitter has just been compromised. We’ve filled tickets and are waiting for answer from X team to regain control. Should be back soon hopefully.
-
Open-Sourcing Jailbreaking Defense Benchmarking Tool
By
–
We’re open-sourcing our code so others can build on our work. We hope it assists in benchmarking misuse risk, and designing defenses to safeguard against strong adaptive attacks. Paper: https://
arxiv.org/abs/2412.03556
GitHub: https://
github.com/jplhughes/bon-
jailbreaking
…
Website: https://
jplhughes.github.io/bon-jailbreaki
ng
… -
Best-of-N Jailbreak Technique Achieves Faster ASR on Claude Models
By
–
Best-of-N can be composed with other jailbreak techniques for even more effective attacks with improved sample efficiency. Combined with many-shot jailbreaking on text inputs, Best-of-N achieves the same ASR 28x faster for Claude 3.5 Sonnet and 70x faster for Claude 3 Opus.
-
Jailbreak Attack Success Rates Scale with Compute Power
By
–
Attack success rates scale predictably with sample size, following a power law. More samples lead to higher success rates; Best-of-N can harness more compute for tougher jailbreaks. This predictable scaling allows accurate forecasting of ASR when using more samples.
-
Best-of-N Jailbreaking Techniques for Vision Language Models
By
–
Best-of-N isn't limited to text. We jailbroke vision language models by repeatedly generating images with different backgrounds and overlaid text in different fonts. For audio, we adjusted pitch, speed, and background noise. Some examples are here: https://
jplhughes.github.io/bon-jailbreaki
ng/#examples
… -
GM Shuts Cruise; Western Chips in Russia; Gemini Advances
By
–
New on @airstreetpress
: Street Talk #2. We share three things that caught our eye this week in AI: 1. Road to nowhere: GM shuttering Cruise 2. To Russia with love: Western chips making their way into Russian weapons 3. Gemini comes of age: GDM cooks! Link below -
Device Security Hardening Targets Spyware Industry Threats
By
–
We are not being unclear. We’re making an important distinction in response to an unsubstantiated rumor. We champion and support work to harden device security and to kneecap the targeted spyware industry that currently profits from making us all less secure.
-
Signal Ensures Data Encryption Privacy Transit
By
–
Signal data is encrypted and private in transit.
-
Signal Denies Vulnerability Rumor Reiterates Open Source Code
By
–
PSA: we've addressed this rumor repeatedly. Tldr there is no evidence of a vulnerability in Signal, and our code is open source.
— Meredith Whittaker (@mer__edith) 13 décembre 2024
No report of this issue was ever made to security@signal.org, and no CVE was filed. There is no truth to the assertion that a phone number enables… https://t.co/YoFMpFMUitPSA: we've addressed this rumor repeatedly. Tldr there is no evidence of a vulnerability in Signal, and our code is open source. No report of this issue was ever made to security@signal.org, and no CVE was filed. There is no truth to the assertion that a phone number enables