No abstract

No abstract

Despite its great success, deep learning severely suffers from robustness; that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones. Inspired by recent advances in brain science, we propose the Denoised Internal Models (DIM), a novel generative autoencoder-based model to tackle this challenge. Simulating the pipeline in the human brain for visual signal processing, DIM adopts a two-stage approach. In the first stage, DIM uses a denoiser to reduce the noise and the dimensions of inputs, reflecting the information pre-processing in the thalamus. Inspired from the sparse coding of memory-related traces in the primary visual cortex, the second stage produces a set of internal models, one for each category. We evaluate DIM over 42 adversarial attacks, showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness.

During a routine dissection of the right upper limb of a 65-year-old male cadaver whose death is not clear, we found two anatomical abnormalities on the musculocutaneous nerve and brachial artery on the same arm. First, the musculocutaneous nerve derived from the lateral fascicles of brachial plexus by two branches. Second, the brachial artery emitted the radial and ulnar arteries at the level of 1/3 proximal upper arm. Given these variations are discovered rarely and accurate knowledge of such variations is important for both surgeons and radiologists.