Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 13 papers Another 247 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 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包
Published Oct 7
Evaluated models Qwen2.5-Coder-7B , Qwen3-Coder-30B , Devstral-Small-2-24B and others19 Abstract PackHallu 诱导规则文件换包。PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。
提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出
Published Oct 7
Evaluated models Qwen3-8B , Qwen3-VL-8B-Instruct , Gemma-4-12B Abstract 论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。
提出 SAGE，定位代码修复 Agent 最早偏离安全意图的轮次
Published Oct 5
Evaluated models GPT-5.5 , Claude Opus 4.8 , Gemini 3.1 Pro and others6 Abstract SAGE 在已通过检查的修复轨迹上定位静默失败的最早偏离，类型比轮次更稳定。SAGE 在已通过语法和功能检查、但仍含确认安全缺陷的智能体修复轨迹上，定位最早可归因的安全意图偏离。 。
提出 EviLLM，经账户指令或插件向代码生成流程注入漏洞
Published Oct 3
Evaluated models GPT-4o , Llama 3.2 (3B) 提出 JIL 对抗后缀，压低长度预测以抬高请求调度优先级
Published Oct 2
Evaluated models Llama-3-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 and others4 Abstract JIL 用对抗后缀压低长度预测，在预测式 LLM 调度中提高自身优先级。JIL 是对预测式 LLM 调度的攻击：用对抗后缀压低长度预测，使请求在 SRPT 式队列里更早得到服务。
测量间接提示注入对类型化概率决策的动作劫持
Published Sep 24
Evaluated models jev-1.13.0 Abstract 封闭动作集改变提示注入的表现，但没有去掉概率被不可信内容移动的风险。作者在 jev-1.13.0 上研究 decision hijacking：不可信内容能否在用户任务和可选动作都不变时，把类型化决策推向攻击者目标。
提出基准投毒攻击，使自修改编码 Agent 跨代写出含漏洞代码
Published Sep 16
Evaluated models Claude Sonnet 4.5 , Qwen3.5-397B , gpt-oss-120b and others5 Abstract 论文报告了恶意基准能污染自修改代码智能体的进化过程并持续输出漏洞，警示系统设计需纳入安全约束。
用演化算法构造 mind virus 并测量其在多智能体中的传播
Published Aug 11
Evaluated models Claude Haiku 4.5 , Claude Sonnet 4.6 , Gemini 3 Flash and others7 提出 SecureForge，在推理时优化系统提示以减少编码智能体的代码弱点
Published May 9
Evaluated models Qwen 2.5 Coder 7B , Qwen 2.5 Coder 14B , Qwen3 30B-A3B and others10 Abstract SecureForge 审计良性 CWE 失败并优化系统提示词。SecureForge 是一条只用 API 和静态分析、在推理时加固编码模型的流水线。
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。
评测代码 Agent 过滤静态告警误报的能力
Published Jan 30
Evaluated models Claude Sonnet 4 , DeepSeek Chat , GPT-5 Abstract 智能体可去掉大量 SAST 噪声，但收益随骨干和 CWE 变化，并会把部分真漏洞标成误报。这是对三种 LLM 智能体框架过滤 SAST 误报的比较研究。
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 Attacks arXiv 2509.05372 · Sep 4, 2025 用对抗缺陷报告诱导自动程序修复系统生成不安全补丁
Published Sep 4, 2025
Evaluated models claude-sonnet-4-20250514 , o4-mini , GPT-4.1-mini and others8 You have reached the end