Signals 4 · free daily AI digest

OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks

Paper recorded by Signals 4 on 2026-08-30 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-30 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.CL · 自然语言处理 · first seen 2026-09-01

Abstract

Different attack methods follow different search trajectories, they succeed on different subsets of samples, whereas existing hard-label black-box text attacks mainly focus on improving individual attackers or manually combining them. We present {\OURS}, a method for optimizing attacker sequences in hard-label black-box text attacks. {\OURS} first performs a one-time bi-objective attack chain sear

Read on arXiv →

#169 most recent of 186 cs.CL papers we have recorded · ↑ newer: Which one is banana man? Evaluating vision-language models in multi-tu · ↓ older: Argument-Aware Semantic Alignment of Normative Texts: A Toulmin-Based
Cite this page: OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks: the #169 most recent of 186 cs.CL papers we have recorded (as of 2026-08-30). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/oasis-optimizing-attacker-sequences-for-hard-label-black-box-text-attacks.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions