Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 240 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 StegoMemory，评测智能体持久记忆作为跨会话隐写信道
Published Oct 3
Evaluated models Llama 3.1 405B , Claude 3.5 Sonnet , GPT-4o and others13 Abstract 研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密，写入持久化是主要防御瓶颈，呼吁建立记忆完整性防御。
提出 GhostWord 词级触发后门，对自动语音识别做数据投毒
Published Sep 2
Evaluated models Whisper-Small , Whisper-Medium , MMS and others4 提出 MAFIA，以探测放置与事实伪装对带审计 Agent 做查询式记忆投毒
Published Aug 4
Evaluated models gpt-5.4-mini , Gemini , ProtectAI and others8 提出 CFD 跨会话分解攻击，利用工件来源缺口绕过工具型 Agent 的本地检查
Published Jun 8
Evaluated models GPT-4.1 , GPT-5-nano , Claude-3.5-Sonnet and others6 Abstract CFD 用无指令 artifact 把越狱拆到跨会话。CFD 针对工具型 LLM 智能体：利用 artifact 来源不被跟踪这一部署失败模式，把有害目标拆开后延迟组合。
提出 SpeechJBB，评测语码转换语音下音频语言模型的越狱稳健性
Published Jun 4
Evaluated models Qwen2.5-Omni-7B , Qwen3-Omni-30B-A3B-Instruct , Voxtral-Small-24B and others9 Abstract SpeechJBB 用五语语码转换语音和伪词探针评测九个 LALM，作者将越狱归为对齐失败而非听不懂。SpeechJBB 用合成语音测量 LALM 在五语、语码转换和局部伪词混淆下的安全对齐，并另设口语理解对照。
Proposes LAAF, which automatically attacks LPCI vulnerabilities in agent systems in stages
Published Mar 18
Evaluated models gemini-2.0-flash-001 , claude-3-haiku-20240307 , meta-llama/llama-3.1-70b-instruct and others5 Abstract LAAF does LPCI red teaming with taxonomy plus stage seeding.The authors state that LAAF is an automated red-teaming framework built specifically for LPCI in agentic LLMs. The issue to address is that encoded, delayed, and conditionally triggered payloads can persist in memory or RAG and re-enter across sessions, whereas Garak and PyRIT do not use the previous round's breakthrough results to seed the next stage across the six stages.
Attacks arXiv 2507.10457 · Jul 15, 2025 提出 LPCI，把延迟条件载荷写入记忆与检索库以跨会话触发
Published Jul 15, 2025
Evaluated models ChatGPT , Claude , LLaMA3 and others8 Abstract 作者定义 LPCI。作者把LPCI 定义为针对智能体逻辑执行、记忆留存和工具集成的跨阶段漏洞类，而不是单次输入上的提示改写。
Attacks arXiv 2504.01094 · Apr 2, 2025 提出 MULTI-AUDIOJAIL，以多语多口音和声学扰动越狱音频模型
Published Apr 2, 2025
Evaluated models Qwen2-Audio , DiVA-llama-3-v0-8b , MERaLiON-AudioLLM-Whisper-SEA-LION and others5 Abstract 黑盒多语多口音音频加声学扰动可抬高 LALM 的 JSR，文本示范防御并非在每个模型上都下降。
You have reached the end