Confusing and Detecting ML Adversarial Attacks with Injected Attractors (2003.02732v4)

Abstract: Many machine learning adversarial attacks find adversarial samples of a victim model ${\mathcal M}$ by following the gradient of some attack objective functions, either explicitly or implicitly. To confuse and detect such attacks, we take the proactive approach that modifies those functions with the goal of misleading the attacks to some local minimals, or to some designated regions that can be easily picked up by an analyzer. To achieve this goal, we propose adding a large number of artifacts, which we called $attractors$, onto the otherwise smooth function. An attractor is a point in the input space, where samples in its neighborhood have gradient pointing toward it. We observe that decoders of watermarking schemes exhibit properties of attractors and give a generic method that injects attractors from a watermark decoder into the victim model ${\mathcal M}$. This principled approach allows us to leverage on known watermarking schemes for scalability and robustness and provides explainability of the outcomes. Experimental studies show that our method has competitive performance. For instance, for un-targeted attacks on CIFAR-10 dataset, we can reduce the overall attack success rate of DeepFool to 1.9%, whereas known defense LID, FS and MagNet can reduce the rate to 90.8%, 98.5% and 78.5% respectively.