Backend
Propose with the Gradient, Accept with the Loss: One Hedged Attack for Pixel-Sparse Robustness
arXiv cs.CR0 views
arXiv:2611.22596v1 Announce Type: cross Abstract: A pixel-sparse adversary may change a few pixels of an image to any value. Robustness to such attacks is currently measured with an ensemble, sparse-AutoAttack (sAA), because its members fail in different places: sparse projected gradient descent (sPGD) trusts a first-order model that a full pixel change breaks, and sparse random search (Sparse-RS) ignores the gradient even where it is informative. We show that both attacks are local searches, each a proposal distribution plus an acceptance rule, and ask what such a search can learn from the gradient. A Taylor bound says what to measure, and measurements at the states the search visits give five rules. The sign of the gradient is its most reliable use at a single pixel and sets a new pixel's value. Its ranking of candidate pixels should be followed loosely, and its ranking of the pixels to remove, which is often more reliable, can be followed more closely. A pixel should not be proposed twice before a move is accepted, and acceptance should be decided by the loss alone. These rules define Gradient-guided Random Search (GRS), which runs once and costs one forward and one backward pass per step. On 13 CIFAR-10 configurations and 5 ImageNet models, GRS matches or beats the best single member of sAA and is within one point of sAA itself or stronger on 17 of 18 settings, and it is significantly stronger than sAA on 8. It uses 3 instead of up to 7 forward-pass units, and on CIFAR-10 it runs 3.7 to 5.0 times faster than the members of sAA run in full.
Source:https://arxiv.org/abs/2611.22596PreviousDexFormer 2.0: Towards a Cross-Embodiment Foundation Policy for Dexterous GraspingNextHE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption
Related posts
Our Guard Checked That We Still Talked About the Fix, Not That We Still Did It
0dev.to

How to Build an Invoice App with Next.js and Firebase Using Claude (With Prompts Included)
0dev.to
One calendar URL, five subscribe links, and the Outlook one Microsoft has never documented
0dev.to
The Hidden Engineering Challenge Behind Smart Construction Sites
0dev.to
WooCommerce Orders Stuck on Pending Payment: How to Fix
0dev.to
WordPress Staging Site: How to Test Changes Safely
0dev.to