The watermark Aaronson proposed is much more subtle than that, and isn't detectable within a text editor. The watermark exists only in the inter-token frequency distributions, and can't be checked without complicated code.
SECURITY
-
AI Personal Timeline: Tracking Goals While Preserving Privacy
By
–
3/Alon Halevy envisions AI capturing massive amounts of data from your daily life — photos, browsing, purchases — and fusing it into a personal timeline that helps you track and achieve your goals, while preserving privacy.
-
Prompt Injection Discovery and Attribution: A History Correction
By
–
A history correction: I am not the first to discover prompt injection. I was merely the first to do so and discuss it publicly. PI was discovered independently by multiple teams. The first was Preamble, an LLM security company, whose find predates mine by several months.
-
Differential Privacy and Secure Aggregation in Federated Learning
By
–
It's a bit complicated. Methods like differential privacy and secure aggregation on top of FL generally help, but there are some caveats. See "Is it possible to Prevent Our Passive and Active Attacks?" of http://
cleverhans.io/2022/04/17/fl-
privacy.html
…. -
Federated Learning: Heterogeneity and Privacy Perspectives
By
–
I like FL as a lens through which to study heterogeneity in clients, which may have different distributions, resources, or capabilities. But not for privacy. Here is another perspective on privacy of FL, which is a bit more conspiratorial than my own https://
x.com/le_science4all
/status/1602432680657928193
… -
Federated Learning Privacy Misconceptions Debunked
By
–
~30% of true/false voters made the biggest misconception in privacy-preserving ML. Fact: federated learning is not private. @jasondeanlee and @tomgoldsteincs posted some nice papers showing this. Also, here's a blog explainer I like by @fraboeni et al.: http://
cleverhans.io/2022/04/17/fl-
privacy.html
… -
Closing Cybersecurity Gaps in Healthcare: 2022 Review
By
–
Closing #CyberSecurity Gaps in #healthcare 2022 in Review! @ATTBusiness #Health & #Security #research See http://
bit.ly/CyberHealthC #AI #5G #ATTInfluencer #CES2023 @RocketVRHealth @DAO_EHT @1OFFGINGER @moingshaikh @tobiaskintzel @ILoveBooks786 @RosyCoaching @SpirosMargaris -
NVIDIA Releases Extended Model Cards for Trustworthy AI
By
–
We made further headway towards enabling trustworthy AI at scale. We released extended model cards at @nvidia with model-specific information concerning bias, explainability, privacy, safety, and security.
-
Nation-States Must Develop Generative AI National Security Strategy
By
–
7. National Security: Major nation-states will start thinking about a national strategy for Generative AI. If they don’t, they should — not having one will put them at a geopolitical disadvantage.