Skip to main content
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:11:07
12 May 2022

Deep neural networks (DNNs) are shown to be vulnerable to a few carefully chosen bit flips in their parameters, and bit flip attacks (BFAs) exploit such vulnerability to degrade the performance of DNNs. In this work, we show that DNNs with high sparsity that typically result from weight pruning have a unique source of vulnerability to bit flips when their coordinates of nonzero weights are attacked. We propose SparseBFA, an algorithm that searches for a small number of bits among the coordinates of nonzero weights when the parameters of DNNs are stored using sparse matrix formats. Using SparseBFA, we find that the performance of DNNs drops to the random-guess level by flipping less than 0.00005% (1 in 2 million) of the total bits.

More Like This

  • SPS
    Members: $10.00
    IEEE Members: $22.00
    Non-members: $30.00
  • CIS
    Members: Free
    IEEE Members: Free
    Non-members: Free
  • CIS
    Members: Free
    IEEE Members: Free
    Non-members: Free