3 Jul 2002: Advogato is now running an implementation of the generic metadata engine described below. The code is available at the mod_virgule CVS, hosted on casper.
Jesse Ruderman » The Advogato trust metric is not attack-resistant
The project for the graduate algorithms class I took in Fall was to compare two algorithms for a problem of our choice. I chose to compare two trust metrics, the Advogato trust metric and Google's PageRank. Trust metrics attempt to solve the following problem: "Given a directed graph where an edge from A to B means 'A trusts B', whom should I trust?".
FAIR Metadata Check (Extended): the FAIR rubric for any repository
ATProtocol Attestations: Cryptographic Signatures for the Decentralized Web - Nick's Blog
This post introduces the formal ATProtocol attestation specification, a framework for adding cryptographic signatures to ATProto records through two complementary patterns: inline attestations that embed signatures directly in records, and remote attestations that store proof in separate repository records. The specification prevents replay attacks through repository binding, uses CID-based content addressing for integrity, and provides the cryptographic foundation for verified credentials, trusted content, and authenticated interactions in the decentralized ATProtocol ecosystem.
Trusted Assertions by vitorpamplona · Pull Request #1534 · nostr-protocol/nips
Certain calculations in Nostr require access to the entire dataset of events and are impossible to do directly by Clients. This PR offers a simple way for users to declare trust in service provider...
ATProtoFans - Support Your Favorite Creators
Decentralized supporter attestation service for the ATProtocol ecosystem. Support creators with cryptographically verifiable relationships.
ATProtoFans - Support Your Favorite Creators
Decentralized supporter attestation service for the ATProtocol ecosystem. Support creators with cryptographically verifiable relationships.
Building Unforgeable Professional Endorsements with ATProtocol - Nick's Blog
Traditional professional endorsements on platforms like LinkedIn lack cryptographic proof—anyone could forge them, and the platform controls the truth. This article introduces a two-record architecture using ATProtocol's Content Identifiers (CIDs) and Decentralized Identifiers (DIDs) to create mathematically unforgeable mutual attestations. By separating proof creation from endorsement acceptance and leveraging the firehose for distributed validation, we build a system where both parties cryptographically consent and no central authority can manipulate the record.
Meta CIB / ATP Dashboard
A comprehensive intelligence platform analysing 214 coordinated inauthentic behaviour and adversarial threat operations identified by Meta across 70 countries, spanning April 2018 to Q4 2025.
Defeating Prompt Injections by Design
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, securing it even when underlying models are susceptible to attacks. To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query; therefore, the untrusted data retrieved by the LLM can never impact the program flow. To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows by enforcing security policies when tools are called. We demonstrate effectiveness of CaMeL by solving $77\%$ of tasks with provable security (compared to $84\%$ with an undefended system) in AgentDojo. We release CaMeL at https://github.com/google-research/camel-prompt-injection.
Web of Trust - Vertrauen durch echte Begegnungen
Dezentrales Vertrauensnetzwerk für lokale Gemeinschaften. Menschen vernetzen sich basierend auf echten Begegnungen statt Algorithmen.
Building Software for a Zero Trust World
How we are helping to build Zero Trust architectures that safeguard the most protected data in the world
Trust Infrastructure on ATproto
I agree with Nick that you have noted a big hard problem, with Zooko’s triangle type trade-offs. (For a semi-related example that is “easier” but still crazy difficult, see our “PeerFlow: Secure Load Balancing in Tor” https://doi.org/10.1515/popets-2017-0017 ) As noted or implied already in this thread: in the end, if someone can cheaply spin up indefinite unlinked identities and build good reputations for them, and if trust is based on such reputations, it is hard (impossible?) to avoid them s...
Confidential Inference via Trusted Virtual Machines
Announcing a new collaborative research paper on Confidential Inference, a set of tools to improve the security of our model weights and of our users' data
As atproto matures, adversarial actors will reveal all the places where trust is implicit rather than managed - maybe time to build reputation mechanisms for PDSs like we do for email servers? It'll likely need to be default-block/prove-healthy, or default throttle until proven typical?
Scoiattolo
They've got a huge network that I'm in the process of graphing. They're now setting up their own PDSes. It's sophisticated.
As atproto matures, adversarial actors will reveal all the places where trust is implicit rather than managed - maybe time to build reputation mechanisms for PDSs like we do for email servers? It'll likely need to be default-block/prove-healthy, or default throttle until proven typical?
Scoiattolo
They've got a huge network that I'm in the process of graphing. They're now setting up their own PDSes. It's sophisticated.
