On Success and Simplicity: A Second Look at Transferable Targeted Attacks
Zhengyu Zhao, Zhuoran Liu, Martha Larson

TL;DR
This paper reveals that simple, data-free targeted attacks using a logit loss can achieve high transferability across models, challenging the belief that complex, resource-intensive methods are necessary.
Contribution
It demonstrates that straightforward, training-free targeted attacks with a logit loss are highly effective, especially in realistic transfer settings, and encourages more meaningful evaluation practices.
Findings
Simple logit loss yields competitive transferability.
Effective targeted universal perturbations can be generated without data or training.
New transfer settings reveal limitations of previous evaluation methods.
Abstract
Achieving transferability of targeted attacks is reputed to be remarkably difficult. Currently, state-of-the-art approaches are resource-intensive because they necessitate training model(s) for each target class with additional data. In our investigation, we find, however, that simple transferable attacks which require neither additional data nor model training can achieve surprisingly high targeted transferability. This insight has been overlooked until now, mainly due to the widespread practice of unreasonably restricting attack optimization to a limited number of iterations. In particular, we, for the first time, identify that a simple logit loss can yield competitive results with the state of the arts. Our analysis spans a variety of transfer settings, especially including three new, realistic settings: an ensemble transfer setting with little model similarity, a worse-case setting…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Advanced Malware Detection Techniques
