← 研踪 PaperTrailarXiv:2610.36422 · v1
What Victims Take Away: Attack Reuse and Defense Revision after Prompt-Injection Attacks
首次提交 2026-10-27 08:04
版本更新 2026-10-27 08:04
雷达观测 2026-10-29 00:35
摘要
Attack logs and red-team reports show targets the attacks used against them, to help them repair their defenses. Prompt injections against large language models (LLMs) are plain text, so such records also hand targets a working copy. Drawing on social learning theory and work on the victim-offender overlap, we study what targets do with that copy in Tensor Trust, an online game whose players defended LLM-guarded accounts, attacked one another's, and could read every attack they received. Using all 563,349 attack records, we compare each received attack with matched attacks that circulated among similar players at the same moment but never reached the target. Reuse mainly followed success: within a week, targets attacked other players with 10.0% of the attacks that had broken their defense, versus 0.03% of matched attacks (adjusted difference: 8.8-10.0 percentage points). Near-misses, whose replies began with "access granted" but that scored as failures, were reused about as rarely as failures: reuse tracked whether an attack paid off, not how its reply read, consistent with payoff-biased social learning. Breaches were also followed by defense changes, after which same-family attacks became 24.5 percentage points less successful against the target, relative to other defenders. Reuse came mainly from players already attacking, not newcomers. Previously received texts accounted for 23.2% of the successful hijacks we analyze. The attack history thus served both repair and reuse; we derive testable hypotheses for how AI security tools should disclose attacks, such as describing the technique without the full text.
作者备注：20 pages, 5 figures, 10 tables. Working paper
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-27 08:04 · 最新观测版本
What Victims Take Away: Attack Reuse and Defense Revision after Prompt-Injection Attacks
Attack logs and red-team reports show targets the attacks used against them, to help them repair their defenses. Prompt injections against large language models (LLMs) are plain text, so such records also hand targets a working copy. Drawing on social learning theory and work on the victim-offender overlap, we study what targets do with that copy in Tensor Trust, an online game whose players defended LLM-guarded accounts, attacked one another's, and could read every attack they received. Using all 563,349 attack records, we compare each received attack with matched attacks that circulated among similar players at the same moment but never reached the target. Reuse mainly followed success: within a week, targets attacked other players with 10.0% of the attacks that had broken their defense, versus 0.03% of matched attacks (adjusted difference: 8.8-10.0 percentage points). Near-misses, whose replies began with "access granted" but that scored as failures, were reused about as rarely as failures: reuse tracked whether an attack paid off, not how its reply read, consistent with payoff-biased social learning. Breaches were also followed by defense changes, after which same-family attacks became 24.5 percentage points less successful against the target, relative to other defenders. Reuse came mainly from players already attacking, not newcomers. Previously received texts accounted for 23.2% of the successful hijacks we analyze. The attack history thus served both repair and reuse; we derive testable hypotheses for how AI security tools should disclose attacks, such as describing the technique without the full text.
查看此版本解读 →查看此版本原文 ↗