Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 11 papers Another 215 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.
提出闭环激活引导，在扩散语言模型去噪过程中注入定向偏见
Published Oct 5
Evaluated models LLaDA-8B-Instruct , Dream-v0-Instruct-7B , LLaDA-MoE-7B-A1B-Instruct Abstract 通过去噪中间概率反馈动态调节残差流转向，证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。
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 NEEDLE，用权重正交化在已知触发器时去除大模型后门
Published Sep 30
Evaluated models Gemma-3-4B-IT , Qwen3-4B-Instruct-2507 , Gemma-3-12B-IT Abstract NEEDLE 用闭式权重编辑去掉已知触发器的后门，并保住拒绝子空间。
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。
提出 MROP，在发射端推理时纯化输入以抵御训练投毒后门
Published Sep 1
Evaluated models DeepJSCC , SwinJSCC Abstract MROP 不重训练，在发射端纯化补丁后门。MROP 是 deep JSCC 无线图像传输上的推理时输入纯化，对象是矩形补丁后门。
用通用扰动对恶意软件分类器及漂移检测器做规避与后门投毒
Published Aug 4
Evaluated models MLP 100-100 , CADE (CAE 512-384-256-128) , CADE (CAE 512-128-32-8) and others6 Mitigating steering dataset contamination with Lee-Valiant robust means
Published Mar 4
Evaluated models Llama-3.2-3B-Instruct , Mistral-7b-Instruct-v0.3 , OLMo-2-1124-7B-Instruct Abstract Data poisoning can alter steering; coordinated injection is strongest.The authors study how much behavioral control remains at inference time when contrastive steering's training data is contaminated, and whether the robust mean can catch it .
Proposes TFL targeted bit flipping so that selected prompts output false answers while unrelated queries remain correct
Published Feb 20
Evaluated models Qwen3-8B , DeepSeek-R1-Distill-Qwen-14B , LLaMA-3.1-8B-INSTRUCT Abstract TFL searches weight bits on three LLMs to make specified prompts produce target keywords while constraining degradation on unrelated tasks.TFL is a framework for targeted bit flips on LLM main memory weights: the attacker wants a selected prompt to output a specified false answer keyword while limiting degradation on unrelated queries.
提出推理扫描器，在仅有模型文件时检测后门并重构触发词
Published Feb 3
Evaluated models gemma-3-270m-it , DeepSeek-R1-Distill-Qwen-1.5B , Phi-4-mini-instruct and others8 Abstract 用记忆泄漏和内部信号重构触发词。这是一个只做推理的 sleeper agent 扫描器：在不知触发词和目标行为时，检测因果语言模型里的条件后门并重构触发词。 。问题在于，后门只在触发词出现时偏离基线，而开放仓库和网页投毒使检测方通常没有触发词、目标或激活语料。
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。
提出 TFA 与 SVA，抑制 ensemble 后门指纹验证
Published Jan 7
Evaluated models LLaMA2-7B , LLaMA3.1-8B-It , Qwen2.5-7B and others11 Abstract 两种 ensemble 攻击 TFA/SVA 抑制后门指纹。TFA 与 SVA 是针对后门式 LLM 指纹的 ensemble 抑制攻击，不改模型参数。所有者用 SFT 写入秘密对，只通过 API 验证版权。攻击者未授权取得模型，不知道触发和指纹，却要把每个模型的验证变成失败，同时让 ensemble 至少不差于性能最高的单模型。
You have reached the end