Risheng Liu, Xuan Liu, Yaohua Liu, Xin Fan, Jiaxin Gao, Xianghao Jiao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Transfer attacks generate significant interest for real-world black-box applications by crafting transferable adversarial examples through surrogate models. Whereas, existing works essentially directly optimize the single-level objective w.r.t. the surrogate model, which always leads to poor interpretability of attack mechanism and limited generalization performance over unknown victim models. In this work, we propose the BilEvel Transfer AttacK (BETAK) framework by establishing an initialization derived bilevel optimization paradigm, which explicitly reformulates the nested constraint relationship between the Upper-Level (UL) pseudo-victim attacker and the Lower-Level (LL) surrogate attacker. Algorithmically, we introduce the Hyper Gradient Response (HGR) estimation as an effective feedback for the transferability over pseudo-victim attackers, and propose the Dynamic Sequence Truncation (DST) technique to dynamically adjust the back-propagation path for HGR and reduce computational overhead simultaneously. Meanwhile, we conduct detailed algorithmic analysis and provide convergence guarantee to support non-convexity of the LL surrogate attacker. Extensive evaluations demonstrate substantial improvement of BETAK (e.g., 53.41% increase of attack success rates against IncRes-v2 ens ) against different victims and defense methods in targeted and untargeted attack scenarios.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.02064")
get_code_for_paper("2406.02064")
have("2406.02064")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.02064.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.02064)
Connect an agent — have() is free.