Skip to main content
Search

Jonathan Pan

1 related articles

Subscribe to updates
  1. arXiv

    Without a restart or code change, a debugger lifts per-layer hidden states from a live GPU, calling refusal at AUROC 0.88

    For an online large-model service that cannot be restarted or modified, existing memory forensics recovers only static artifacts such as weights or prompt logs, not the per-layer hidden states that exist briefly on the GPU during a single request. A six-stage pipeline built on a non-modifying debugger uses either a PyTorch allocator clock or a kernel-launch clock to identify and read tensor allocations in video memory, recovering bytes byte-exactly on 33 open-source decoder-only models across nine architecture classes. Linear probes trained on ordinary framework activations, applied to those recovered states, separate refusal from compliance on 142 untouched prompts at an AUROC of 0.876, with a false-positive rate of 0.282.

You’re all caught up