# Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

Source: [Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks](<https://www.sota2.com/research/paper/6a152949dbd7150506f7e1ab>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-27T05:00:21.000Z

Authors: Florent Tariolle, Florian Yger

Published: 2026-05-25T10:14:06.000Z

## Abstract

Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected progress. We introduce Opportunistic Target Selection (OTS), a lightweight wrapper that switches an untargeted attack to a targeted objective early in its trajectory, locking onto whichever non-true class currently leads. OTS requires no architectural modification to the underlying attack, no gradient access, and no a priori target-class knowledge.   We validate OTS on three score-based attacks (SimBA, Square Attack with cross-entropy loss, and Bandits) across five standard ImageNet classifiers (4,500 runs). On random-search attacks, OTS closely tracks oracle performance, with gains up to +27 pp in success rate and 43% relative reduction in censored-mean iterations on ResNet-50. On gradient-estimation attacks (Bandits) and attacks with margin loss, OTS is redundant, a negative result that reinforces our interpretation of OTS as a margin-loss surrogate. On adversarially-trained models, a bimodal difficulty distribution eliminates the regime where targeting helps.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Adversarial Attack on ILSVRC 2012 (val)](<https://www.sota2.com/research/sota/adversarial-attack-on-ilsvrc-2012-val.md>): Adversarial Attack; ILSVRC 2012 (val); Median L2 Distance: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.25663>)

[PDF](<https://arxiv.org/pdf/2605.25663.pdf>)
