home.social

#oneflip — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #oneflip, aggregated by home.social.

  1. cs.gmu.edu/~zeng/papers/2025-S

    #oneflip : one flip to rule them all.

    The linked paper by students of George Mason University (Xiang Li et al (2025): "Rowhammer-Based Trojan Injection:
    One Bit Flip Is Sufficient for Backdooring DNNs") descibes how flipping a single bit suffices to corrupt the output of high-precision a.i.-s based on deep neural networks.

    Of course there are no mitigations: none of the creators imagined malice.

    #cybersecurity #aisecurity

  2. cs.gmu.edu/~zeng/papers/2025-S

    #oneflip : one flip to rule them all.

    The linked paper by students of George Mason University (Xiang Li et al (2025): "Rowhammer-Based Trojan Injection:
    One Bit Flip Is Sufficient for Backdooring DNNs") descibes how flipping a single bit suffices to corrupt the output of high-precision a.i.-s based on deep neural networks.

    Of course there are no mitigations: none of the creators imagined malice.

    #cybersecurity #aisecurity

  3. cs.gmu.edu/~zeng/papers/2025-S

    #oneflip : one flip to rule them all.

    The linked paper by students of George Mason University (Xiang Li et al (2025): "Rowhammer-Based Trojan Injection:
    One Bit Flip Is Sufficient for Backdooring DNNs") descibes how flipping a single bit suffices to corrupt the output of high-precision a.i.-s based on deep neural networks.

    Of course there are no mitigations: none of the creators imagined malice.

    #cybersecurity #aisecurity

  4. cs.gmu.edu/~zeng/papers/2025-S

    #oneflip : one flip to rule them all.

    The linked paper by students of George Mason University (Xiang Li et al (2025): "Rowhammer-Based Trojan Injection:
    One Bit Flip Is Sufficient for Backdooring DNNs") descibes how flipping a single bit suffices to corrupt the output of high-precision a.i.-s based on deep neural networks.

    Of course there are no mitigations: none of the creators imagined malice.

    #cybersecurity #aisecurity

  5. cs.gmu.edu/~zeng/papers/2025-S

    #oneflip : one flip to rule them all.

    The linked paper by students of George Mason University (Xiang Li et al (2025): "Rowhammer-Based Trojan Injection:
    One Bit Flip Is Sufficient for Backdooring DNNs") descibes how flipping a single bit suffices to corrupt the output of high-precision a.i.-s based on deep neural networks.

    Of course there are no mitigations: none of the creators imagined malice.

    #cybersecurity #aisecurity