Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 22 papers Another 227 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.
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 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。
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 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.
提出 FERRET 框架，用扩展生成多轮多模态越狱对话
Published Feb 18
Evaluated models Llama Maverick , Claude Haiku , GPT-4o Propose MAPA multi-turn adaptive prompt attack, alternating text and visual actions to jailbreak vision-language models
Published Feb 16
Evaluated models LLaVA-V1.6-Mistral-7B , Qwen2.5-VL-7B-Instruct , Llama-3.2-Vision-11B-Instruct and others4 提出 MM-Plan 多模态越狱框架，自动规划多轮图像编辑以越狱视觉独占目标
Published Feb 5
Evaluated models Llama-3.2-11B , InternVL3-8B , Qwen3-VL-8B and others8 Abstract 作者称全局规划能攻破对单轮攻击更稳的前沿 MLLM。MM-Plan 是面向 Visual Exclusivity 的 black-box 多模态红队方法，并配有人工基准 VE-Safety。
提出 JustAsk，用在线技能选择提取模型系统提示词
Published Jan 29
Evaluated models anthropic/claude-opus-4.5 , openai/gpt-5.2-codex , GPT-5.2 and others19 提出 ICON 多轮越狱，用意图-上下文先验生成攻击序列
Published Jan 28
Evaluated models Llama-4-Maverick-Instruct , Llama-3.1-405B-Instruct , Qwen-Max-2025-01-25 and others11 提出知识驱动多轮越狱 Mastermind，用策略知识闭环攻击对齐模型
Published Jan 9
Evaluated models Llama 3.1 8B Instruct , Llama 3.3 70B Instruct , Qwen 2.5 7B Instruct and others16 提出多轮多模态越狱，并用 FragGuard 拦截有害响应
Published Jan 9
Evaluated models LLaVa-1.6 (7B) , LLaVa-1.6 (13B) , Qwen-2-7B and others5 提出无外部攻击模型的多轮自我越狱方法 SLIP
Published Jan 6
Evaluated models GPT-5.1 , GPT-4o , Claude-Sonnet-4.5 and others11 Abstract 论文提出了无外部攻击模型的自我越狱方法 SLIP，指出对齐模型内在能力抑制的漏洞并设计了语义漂移防御。