NAll news

Saturday1 items

Friday1 items

Thursday1 items

Wednesday1 items

Tuesday1 items

Monday1 items

Saturday1 items

Friday1 items

Friday1 items

  1. janleikeResearch
    AI score54

    English translation is being prepared.

    New Anthropic research: Building and evaluating alignment auditing agents. We developed three AI agents to autonomously complete alignment auditing tasks. In testing, our agents successfully uncovered hidden goals, built safety evaluations, and surfaced concerning behaviors. https://t.co/HMQhMaA4v0

    #Safety / alignment#Agents#Anthropic

Wednesday2 items

Tuesday1 items

Wednesday1 items

Saturday1 items

  1. Cato AI LabsFirst-partyResearch
    AI score81

    Aim Labs discloses the complete attack chain of the M365 Copilot zero-click vulnerability EchoLeak

    Aim Labs disclosed the zero-click vulnerability EchoLeak in Microsoft 365 Copilot: an attacker only needs to send a single email to the victim to exfiltrate sensitive data in the Copilot context without the user's awareness. The attack chain consists of three vulnerabilities, which in sequence bypass the XPIA prompt injection classifier, the sanitization of external links and images, and, with the help of SharePoint and Teams URLs, bypass CSP restrictions. Aim Labs calls the core technique LLM Scope Violation and believes that similar design flaws may also exist in other RAG-based chatbots and AI agents, and states that Microsoft has confirmed that no customers were affected.

    #Safety / alignment#RAG#Microsoft

Sunday1 items

Saturday1 items

Thursday1 items

Friday1 items

  1. janleikeResearch
    AI score58

    English translation is being prepared.

    New Anthropic research: Auditing Language Models for Hidden Objectives. We deliberately trained a model with a hidden misaligned objective and put researchers to the test: Could they figure out the objective without being told? https://t.co/fxmA9Os2C9

    #Safety / alignment#English text is being prepared.#Papers/Research

Tuesday1 items

Monday1 items