• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Trigger words reportedly cause DeepSeek-R1 to generate vulnerable code

    CrowdStrike says its researchers identified hidden vulnerabilities in AI-coded software. A user sharing the research warns about potential backdoors in open models.

    EmadEM
    1 Source, 20d ago, first seen 20d ago

    TLDR

    CrowdStrike reports that trigger words cause DeepSeek-R1 to generate vulnerable code, exposing risks in software development. A user sharing the research raises concerns about backdoors that could be put into open models, particularly when those models write code.

    Combined views

    748

    1 Source, first seen 20d ago

    Combined views

    748

    1 Source, first seen 20d ago

    1 likes
    1 likes
    1 saves
    1 reposts
    1 saves
    1 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    Emad@EMostaque@rabois @JayaGup10 Weird type of cognitive colonialism threat as well as the standard security ones. This is particularly pertinent when you consider the types of backdoors when it writes code that can be put into open models https://www.crowdstrike.com/en-us/blog/crowdstrike-researchers-identify-hidden-vulnerabilities-ai-coded-software/20d

    1 Source

    Emad@EMostaque@rabois @JayaGup10 Weird type of cognitive colonialism threat as well as the standard security ones. This is particularly pertinent when you consider the types of backdoors when it writes code that can be put into open models https://www.crowdstrike.com/en-us/blog/crowdstrike-researchers-identify-hidden-vulnerabilities-ai-coded-software/20d