Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
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 MIRROR，用多路径摘要多数表决保障多智能体通信完整性
Published Oct 2
Evaluated models Gemma-4-31B-it , Gemini 2.5 Pro Abstract MIRROR 靠多数路径。MIRROR 是 LLM 多智能体通信层上的多路径法定人数完整性原语，只处理不透明字节，不解释消息内容。要处理的是 Agent-in-the-Middle：中介合法终结 TLS 后可改在途消息，而语义校验有推理开销和误拦，签名又要求私钥管理。做法是生成结束后复制同一规范化载荷。
提出 SeedHijack，劫持采样 PRNG 以强制选定 token
Published May 8
Evaluated models GPT-2 (124M) , Qwen2-1.5B-Instruct , DeepSeek-R1-1.5B and others5 Abstract 采样层 PRNG 被替换以强制选 token。SeedHijack 把 LLM 采样用的 PRNG 输出换成攻击者选定的数，从而指定下一个 token。权重、输入和 logits 都不改。防御是用硬件 QRNG 替换该随机源。
为去中心化 LLM 推理网络提出稳健成本感知 PoQ，抵御恶意评估者操纵分数
Published Jan 29
Evaluated models llama 3 2 3b , gemma 2 2b it , tinyllama 1 1b and others10 Abstract 成本感知 PoQ 加入稳健共识。这篇扩展工作把成本感知 Proof of Quality 的共识层改成能承受恶意评估分数的形式，奖励仍同时看输出质量与延迟成本。
Attacks arXiv 2511.22681 · Nov 28, 2025 提出 CacheTrap，翻转 KV cache 单比特以导向指定类别
Published Nov 28, 2025
Evaluated models LLaMA-2-7B-Chat , LLaMA-3.1-8B-Instruct , Mistral-7B-Instruct-v0.1 and others5 You have reached the end