PulseAugur
EN
LIVE 10:10:17
ENTITY InjecAgent

InjecAgent

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

Show in brief
Total · 30d
3
7 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
3
6 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

3 day(s) with sentiment data

RECENT · PAGE 1/1 · 7 TOTAL
  1. TOOL · CL_169815 ·

    New prompt injection detection techniques leverage cross-domain methods

    Researchers have developed seven novel techniques for detecting prompt injection attacks, moving beyond traditional pattern matching and fine-tuned transformer classifiers. These new methods draw inspiration from divers…

  2. RESEARCH · CL_167426 ·

    New method enhances LLM agent safety by stratifying risk in tool calls

    Researchers have developed a new method called role-stratified per-field conformal risk control to enhance the safety of language-model agents. This technique calibrates risk budgets separately for different semantic ro…

  3. TOOL · CL_160935 ·

    New RL framework PISmith tests and breaks prompt injection defenses

    Researchers have developed PISmith, a novel reinforcement learning (RL) framework designed to rigorously test the effectiveness of prompt injection defenses in large language models (LLMs). The framework trains an attac…

  4. 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…

  5. 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…

  6. 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…

  7. 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…