arXiv (OAI Expanded)
open access
The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks
Input Diversity (DI), a random resize and pad applied at each attack iteration, is a near-default ingredient of transfer-based attacks, widely assumed to improve transferability. We show this assumption is regime-dependent and, for adversarially trained surrogates, often reversed. Holding the attack
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion#1116933
- Feature Separation and Recalibration for Adversarial Robustness#464535
- A Survey on Attacks and Their Countermeasures in Deep Learning: Applications in Deep Neural Networks, Federated, Transfer, and Deep Reinforcement Learning.#489651
- Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples#612542
- Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples#611065
Record · ID 1123137
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive