Researchers from the University of Stuttgart and ELLIS Alicante propose that large reasoning models (LRMs) can act as autonomous jailbreak agents without complex scaffolding, using multi-turn persuasive dialogue to gradually escalate requests and bypass target models' safety measures. Experiments used four adversarial models—DeepSeek-R1, Gemini 2.5 Flash, Grok 3 Mini, and Qwen3 235B—against nine target models—GPT-4o, DeepSeek-V3, Llama 3.1 70B, Llama 4 Maverick, o4-mini, Claude 4 Sonnet, Gemini 2.5 Flash, Grok 3, and Qwen3 30B—each with 10 rounds of dialogue. The benchmark contained 7 categories totaling 70 harmful requests, and the combined jailbreak success rate under this experimental setting was 97.14%. In control experiments, when benchmark items were given directly to target models, the average harm score was below 0.5; when the non-reasoning model DeepSeek-V3 was used as the attacker, the average harm score was only 0.885. The authors argue that reasoning ability plays an important role in these experimental results.
Why it was selectedThe paper uses four reasoning models to perform multi-turn persuasive jailbreaks against nine target models, and provides comparative data on each model's resistance and mitigation attempts.
论文提出类似 OpenClaw 的工具调用型智能体默认不安全,应按系统工程而非模型对齐的思路加固。这类智能体在同一执行循环中叠加不可信输入、自主行动、插件扩展面与特权系统访问四类风险,而多数 AI 安全投入集中在模型层。论文主张转向系统性防御工程:沙箱化运行时隔离、第三方插件治理、最小权限执行,并在 API 边界而非仅提示词层校验工具调用。
一篇论文提出 Colluding LoRA(CoLoRA)攻击,单独加载时看似无害的 LoRA 适配器经线性组合后可广泛压制模型的拒答行为,无需对抗提示或特殊触发词。论文称该攻击发生在模型权重层面,属于针对模型组合的供应链攻击。现有防御在部署前逐个验证适配器,但有害行为只在适配器合并时出现,而穷举所有适配器组合在计算上不可行。论文来自 Mercedes-Benz Research & Development North America,作者称同样的组合逻辑也适用于插件生态、多 Agent 系统和 RAG 管线。
Failure-First 研究项目分析 FDA MAUDE 数据库中 ReWalk 动力外骨骼的多起不良事件,指出可穿戴机器人存在一类被忽视的失效模式。2024 年 9 月一名 ReWalk Personal 6.0 用户在坐站转换中发生胫骨骨折,报告称骨折发生在设备正常运行时;2018 年 1 月一名 ReWalk Personal 5.0 用户的骨盆带在行走中开裂;2017 年 5 月一起骨折被归因于非标准设备故障。文章指出,外骨骼执行器需产生足以让 70-100 kg 成人站起的力量,而脊髓损伤用户伤后数年内股骨和胫骨骨密度可能下降 30-50%,设备却无法感知骨密度、痉挛、疲劳或疼痛。ReWalk 2014 年获 FDA 的 Class II de novo 许可,MAUDE 作为上市后监测系统存在报告质量不一、缺少分母等局限。