收录解读
LLM代理处理外部内容时面临提示注入和多轮操控威胁,但现有安全基准多依赖攻击池固定、单轮或非自适应评估,难以反映真实攻击的演化能力。本文针对无状态LLM防御者,提出覆盖21个场景的自适应多轮攻击基准。
核心方法为自主LLM攻击者根据前序防御响应在多轮间调整策略,同时保持每轮防御交互独立。通过控制场景、攻击者、防御者和结构化输出评分固定,仅将评分限制于首轮攻击时成功率为0-1%,而允许15轮自适应攻击后成功率升至5.4-14.0%。
实验使用三个前沿LLM(Claude Opus 4.6, GPT-5.4, Gemini)进行3×3矩阵评估,收集945份转录和18,422场战斗。多攻击者联合挖掘出比最佳单攻击者多1.4-2.2倍的独特成功攻击,且生成攻击与现有基准余弦相似度仅0.02-0.14。统计显示各防御者排名在不同场景下不一致(Kendall's W=0.19),13/21场景可区分至少一对防御者。
该基准提供了可复用的评估框架、代码、数据和攻击回放集,揭示了单轮评估的局限性及防御间分布差异,但对非前沿LLM的通用性待验证。作为一个实用基准,它有望推动LLM代理安全研究向自适应对抗评估发展,但尚未达到重塑领域蓝图的程度。
原始摘要
LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi-turn. We present a 21-scenario benchmark for \emph{adaptive multi-round attacks against memoryless LLM defenders}: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. Holding the 21 scenarios, attackers, defenders, and structured-output scoring fixed, restricting scoring to the first attacker turn yields $0$-$1\%$ attack success rate (ASR); allowing 15 rounds of adaptive attack yields $5.4$-$14.0\%$. Pooling three frontier attacker LLMs uncovers $1.4$-$2.2\times$ as many unique successful attacks as the best single attacker, and the generated attacks have low cosine similarity ($0.02$-$0.14$) to attacks in existing benchmarks. Claude Opus 4.6 and GPT-5.4 are tied in aggregate ($5.4\%$ each; overlapping $95\%$ CIs), but their weaknesses differ sharply: on one scenario Opus reaches $60\%$ ASR ($95\%$ CI $36$--$80\%$) while GPT-5.4 and Gemini each stay at $7\%$ (CI $1$-$30\%$; the gap is preserved in a higher-$N$ replication). $13$ of $21$ scenarios distinguish at least one defender pair, yet rankings disagree across scenarios (Kendall's $W = 0.19$). We release the benchmark -- 21 evaluation scenarios, 10 public development scenarios, the orchestrator, baseline harnesses, and a multi-attacker CLI -- plus 945 transcripts from the 3$\times$3 frontier matrix, an attack-replay dataset, and 18{,}422 gpt-oss-20b battles from an open competition's final scoring rounds.