PulseAugur
EN
LIVE 22:21:48
ENTITY AgentDojo

AgentDojo

PulseAugur coverage of AgentDojo — every cluster mentioning AgentDojo across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
7
7 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
6
6 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
SENTIMENT · 30D

2 day(s) with sentiment data

RECENT · PAGE 1/1 · 7 TOTAL
  1. TOOL · CL_116442 ·

    Prompt optimization may weaken LLM adversarial robustness, new benchmark suggests

    A new benchmark has been developed to investigate whether prompt optimization techniques for Large Language Models (LLMs) weaken their robustness against adversarial attacks, specifically prompt injection. Initial findi…

  2. TOOL · CL_70446 ·

    LLM attack benchmarks cover less than 25% of threat landscape

    Researchers have developed a new framework to audit the coverage of benchmarks designed to test Large Language Model (LLM) attacks. This framework, based on a taxonomy of over 500 inference-time attacks, reveals that cu…

  3. TOOL · CL_53868 ·

    New Protocol Enables LLMs to Safely Control Small Devices

    Researchers have introduced the Device Context Protocol (DCP), a new architecture designed to enable large language models (LLMs) to safely control constrained devices. DCP is significantly more lightweight than existin…

  4. TOOL · CL_50472 ·

    Arc Gate offers solution to OpenAI's 'unfixable' prompt injection vulnerability

    OpenAI has stated that prompt injection in browser agents is an unfixable structural vulnerability at the model level. However, a new architectural solution called Arc Gate has demonstrated significant success in mitiga…

  5. TOOL · CL_32688 ·

    LLM attack benchmarks show significant gaps in security coverage

    Researchers have developed a new framework to audit the coverage of LLM attack benchmarks, revealing significant gaps in current evaluations. Their analysis of six public benchmarks showed they collectively cover less t…

  6. RESEARCH · CL_16489 ·

    New attack exploits LLM agent relays, bypassing alignment defenses

    Researchers have identified a new vulnerability in LLM agent architectures that use Bring-Your-Own-Key (BYOK) systems. These architectures route LLM traffic through third-party relays, creating an integrity gap where a …

  7. RESEARCH · CL_99526 ·

    New research explores LLM agent evaluation and improvement techniques

    Researchers are exploring new methods for evaluating and improving Large Language Model (LLM) agents. One paper introduces semantic early-stopping for iterative LLM loops, aiming to reduce token usage by halting when me…