Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 33 papers Another 232 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 A2A-TIBA，经 A2A 对等任务间接注入并植入常驻回调
Published Sep 30
Evaluated models MiniMax-M3 , deepseek-v4-pro , glm-5.3 and others8 Abstract A2A-TIBA 一次植入后绕过智能体，GDA 用四类结果定位防线，ELA-ITL 把信封标注列为第三层。A2A-TIBA 把间接提示注入和绕过放进 A2A：gray-box 攻击者已能投递任务，诱导目标部署常驻回调程序后，下令和外传不再经过智能体。
评测多轮对话中 GradSafe 越狱检测的可分性与脆弱性
Published Sep 29
Evaluated models Llama 3.1 8B Instruct , Qwen2.5-7B-Instruct Abstract CWS 显示不安全梯度在真实多轮流量中变弱，且随攻击族和模型而变。作者评估梯度越狱检测从单条提示词迁到多轮对话后还剩多少可分性，方法是用 Context Window Scanner 把 GradSafe 原封不动地套到用户轮窗口上。
提出推理通道预填与输出前缀组合攻击以越狱推理模型
Published Sep 24
Evaluated models Gemini 3 Flash Preview , DeepSeek V4 Flash , Claude Haiku 4.5 提出 plan injection 攻击，植入良性伪装计划以绕过思维链监视器
Published Sep 15
Evaluated models Qwen2.5-Coder-7B-Instruct , Qwen3-8B , DeepSeek-R1-0528 and others6 Abstract 论文指出模型会将外部上下文中的伪装计划改写为自身推理，使思维链监视器失效甚至反向合理化恶意行为。
提出任意字母置换密码越狱，无需微调即可诱导有害输出
Published Sep 9
Evaluated models Claude Sonnet 4 , Claude Sonnet 4.5 , Gemini 3 Flash (preview) and others7 Abstract 前沿大模型无需微调即可通过提示词学会字母置换密码，进而绕过分类器与对齐，作者呼吁关注能力提升带来的安全风险。
揭示推理加深引发的对齐坍塌，用 Reasoning Trap 放大越狱
Published Sep 8
Evaluated models Qwen3-8B , Qwen3-14B , Llama2-7B and others8 Abstract 更深推理提升题目准确率，同时提高扰动下的相对损失。作者研究扩展推理是否以对齐稳健性为代价，提出 ALR、RT 与 RRA。 。
提出 MIPC 与 CFA，观察模型自拟测验后接受开发者身份
Published Sep 3
Evaluated models ChatGPT , Claude , Qwen3.7-Plus and others5 Abstract 自拟测验可造成对话层虚假认证，但所测授权边界并未因此改变。这项工作把“模型自己出题、自己批改、再宣布身份已核验”定义成对话层认证失败，并与后端提权分开。
提出多轮越狱框架 BLUEPRINT，用世界观模拟与心理因素诱导有害输出
Published Sep 2
Evaluated models Qwen3-Next-80B , DeepSeek-V3.2 , GLM-4.7 and others6 Abstract BLUEPRINT 解耦多轮越狱策略与情境模拟，揭示任务具象化是摆脱拒绝的核心机制，为多轮安全防御提供新视角。BLUEPRINT 是一个将因子化社会影响力策略空间与跨轮世界观模拟解耦的多轮大语言模型安全评测框架。
利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链
Published Aug 11
Evaluated models Claude Opus 4.8 , Claude Sonnet 4.6 , Claude Haiku 4.5 and others13 Abstract 论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。
提出面向意图的多轮 LLM 越狱分类体系
Published Aug 2
Evaluated models Llama-3 , Llama-3.3-70B , DeepSeek-V3 and others11 Abstract 作者用四维意图分类整理多轮越狱，并称组织方式影响效果与观察范围。这是一篇关于多轮 LLM 越狱的 SoK：按有害意图在交互中的组织位置分类，而不是按单步提示技巧分类。
提出生物红队模型 Intern-BioBreaker，多轮越狱诱导模型输出可操作生物危害
Published Jul 20
Evaluated models DeepSeek-V3 , Kimi-K2.6 , DeepSeek-V4-Pro and others14 Abstract 论文通过构建专用红队模型评估前沿大模型的生物安全漏洞与物理转化风险。
提出 SMT 框架，用模拟审核轨迹越狱函数调用 LLM
Published Jul 1
Evaluated models GPT-4o , GPT-5.4 , Qwen3-Max and others7 提出 AdvGRPO，用 GRPO 闭环共训多轮越狱攻击者与防御者
Published Jun 9
Evaluated models Qwen2.5-7B-Instruct , Qwen2.5-14B-Instruct , Qwen3.5-9B and others7 构建 MultiTurnPSB，评测四轮医疗越狱与分类器输入防御
Published May 30
Evaluated models GPT-4.1-mini , Claude Sonnet 4.5 Abstract 多轮攻击加剧医疗模型风险，分类器干预有效但受高误报率制约。MultiTurnPSB 针对患者端医疗大模型在持续交互中的安全风险，构建了包含三种攻击模态的四轮对抗评测基准。
提出 Persona Attack，分步写入对话记忆指令以越狱
Published May 29
Evaluated models GPT-4o , Llama-3.2-3B-Instruct , ChatGPT-4o and others5 提出层级遗传算法 HGA，扰动题目逻辑结构诱发推理模型过度思考
Published May 13
Evaluated models DeepSeek-R1 (671B) , Qwen3-Thinking , GPT-o3 and others5 Abstract HGA 在黑盒推理模型上用逻辑扰动拉长输出，作者称可从小代理迁移，查询成本是其局限。
提出多轮意图欺骗越狱 iDecep，用良性意图伪装引出有害内容
Published Apr 27
Evaluated models GPT-4o , Gemini-2.5-Flash , Claude-Sonnet-4.5 and others4 Abstract iDecep 用意图欺骗做多轮越狱，在 GPT-5 与 Claude-Sonnet-4.5 上同时测到直接成功和 para 成功。iDecep 是一种黑盒多轮越狱：用表面良性的意图维持与恶意目标贴近的对话，并单独计入 safe completion 替代内容中的有害信息。 。
Proposes the STAR multi-turn role-playing framework, which bypasses safety alignment through dialogue state evolution
Published Mar 15
Evaluated models GPT-4o , Claude 3.5 Sonnet , Gemini 2.0-Flash and others5 提出多流扰动攻击，交织有害与良性任务绕过思考型 LLM 安全对齐
Published Mar 10
Evaluated models Qwen3 1.7B , Qwen3 4B , Qwen3 8B and others11 Abstract 多流扰动用任务交织测试 thinking 模式，作者称它同时冲击内容安全与推理稳定性。多流扰动攻击把有害任务与良性任务织进同一提示词，测试 thinking 模式的内容安全与推理稳定性。作者认为，交织多任务会拉长思考，使安全检测面对被打散的有害意图，并可能把推理用于合理化，或陷入崩溃与重复。方法不访问梯度。
Using ADVERSA to measure guardrail degradation and reviewer reliability under multi-turn attacks
Published Mar 10
Evaluated models Claude Opus 4.6 , Gemini 3.1 Pro , GPT-5.2 Abstract ADVERSA measures multi-turn guardrail changes using per-turn compliance trajectories and three-reviewer consensus.ADVERSA is an automated multi-turn red-teaming measurement framework that records guardrail behavior as per-turn compliance trajectories and simultaneously measures whether reviewers agree. The problem it addresses: single-turn binary pass/fail cannot show how safety properties change under sustained adversarial pressure, nor can it separate gradual refusal consolidation from stable scores. The authors argue that real-world adversaries rewrite and persist over multiple turns.