Skip to content

Translation in progress Some entries still include text in the original language.

Oct 13 · Tuesday

All papers

Found 201 papers
Filter5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.

Another 201papers do not have category tags yet and are not included in filtered results.

  1. Reward hacking as a transmissible strategy in multi-agent coding systems

    Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems

    Published
    Evaluated models
    Qwen2.5-Coder-14B, Gemma-3-12B, Qwen2.5-Coder-7B and others16
    AbstractThe authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.

    Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.

    Paper analysisRead analysis
  2. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  3. Workerville: Toward an Organizational Behavior Explanation of Agent Safety

    构建 Workerville 基准,测量组织条件如何改变 Agent 的安全行为

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.2, Claude-Sonnet-4.6, Gemini-3.1-Pro and others6
    Abstract作者用 ACB 与 Workerville 测量组织条件对智能体安全的影响,并称结果支持可量化的组织行为框架。

    Workerville 用组织行为测量智能体安全如何随监督、同伴和记忆条件变化。。要处理的缺口是:持续运行的 LLM 智能体同时接收用户指令、同伴消息和长期记忆,但既有安全评测多把这些通道拆开,没有统一的定量测量。

    Paper analysisRead analysis
  4. DefensesarXiv 2610.10345

    SLDR:通过选择性层恢复与动态路由防御恶意微调

    提出 SLDR,用选择性层恢复与动态路由防御恶意微调

    Published
    Attacker
    Black-box
    Evaluated models
    Llama3.1-8B-Instruct, Llama3-8B-Instruct, Qwen2.5-7B-Instruct and others4
    Abstract作者称 SLDR 能压低有害输出并保持下游效用。

    SLDR 是针对恶意微调的微调后防御:在已对齐模型上做有符号层探测,只在敏感分数最大与最小的两层训练 LoRA,再用 lmax 的最后 token 表示决定是否启用适配器。

    Paper analysisRead analysis
  5. DefensesarXiv 2610.09941

    OrthoPurify 用一步正交投影净化被后门污染的视觉语言模型

    提出 OrthoPurify,用正交投影清除视觉语言模型适配器中的劫持方向

    Published
    Evaluated models
    LLaVA-1.5-7B, Qwen3-VL-8B, LLaVA-1.5-13B and others5
    Abstract一次投影去掉劫持方向。

    OrthoPurify 是部署前的 LVLM 后门净化方法,用一次正交投影去掉被劫持的权重更新方向。

    Paper analysisRead analysis
  6. AttacksarXiv 2610.09819

    FAB 攻击:给 HuBERT/WavLM 植入后门,背景警笛声即可让下游语音任务失灵

    提出 FAB 攻击,向声学基础模型植入可由环境声触发的后门

    Published
    Evaluated models
    HuBERT-base, WavLM-base

    Abstract论文提出了针对声学基模的 FAB 后门攻击,在弱威胁模型下实现了任务无关、物理可触发的后门植入。

    Paper analysisRead analysis
  7. DefensesarXiv 2610.09793

    用时序逻辑监控工具 Agent

    提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链

    Published
    Setting
    AI Agent
    Attacker
    Black-box
    Abstract形式化验证可有效识别多步攻击,但其有效性高度依赖轨迹的可信历史记录。

    这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。

    Paper analysisRead analysis
  8. 研究:去除有害信息不足以证明开源权重模型的抗篡改能力

    论证发布时互信息不能认证开源权重抗微调恢复

    Published
    Evaluated models
    EleutherAI/deep-ignorance-e2e-strong-filter, EleutherAI/deep-ignorance-unfiltered, Google BERT-Tiny and others6
    Abstract作者称零信息仍可一步恢复,表观抗微调可来自参数化。

    作者研究开源权重模型的篡改抵抗:发布时的互信息是否足以保证微调恢复很慢。

    Paper analysisRead analysis
  9. 论文提出 agent plasticity 指标衡量智能体通过经验自我改进的效率

    提出 agent plasticity 指标衡量智能体通过经验自我改进的效率

    Published
    Evaluated models
    Claude Fable 5, Claude Opus 5, GPT-5.6 Sol and others10
    Abstract作者用固定权重协议比较前沿模型把经验写成制品后的留出增益与习得效率。

    作者用 agent plasticity 衡量一件事:权重冻结时,智能体把经验写成可继承制品,再换成留出能力增益,这个转换有多省。

    Paper analysisRead analysis
  10. Learn2Play Bench 发布:用规则陌生的文本游戏评测 LLM Agent 从经验中学习的能力

    用 Learn2Play Bench 评测 Agent 从经验中学习陌生规则

    Published
    Setting
    AI Agent
    Evaluated models
    Claude Opus 5.5, GPT-6 Astra, Claude Opus 5 and others11
    Abstract用隐藏规则游戏把新学习与预训练知识分开,并比较模型、记忆方式和人类。

    Learn2Play Bench 用新设计的隐藏规则文本游戏,评测 LLM 智能体在不更新权重时从交互中学习的能力。

    Paper analysisRead analysis
  11. AttacksarXiv 2610.07723

    Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

    提出回答端后门,让模型自生成触发词以在干净有害请求下绕过拒答

    Published
    Evaluated models
    Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4

    Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击,指出输入端防护存在盲区。

    Paper analysisRead analysis
  12. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER,以确定性检查优先拦截多智能体流水线的内容攻击

    Published
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里,确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  13. AttacksarXiv 2610.07654

    研究揭示策略蒸馏的安全后门风险

    测量带后门教师经 OPD 向干净学生迁移潜伏后门

    Published
    Evaluated models
    Qwen2.5-1.5B-Instruct, Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct
    Abstract作者称 OPD 可在压低无触发词有害率时迁入后门。

    带后门的外部教师经 OPD,可在压低无触发词有害率的同时,把触发条件下的有害行为传给初始干净学生。。

    Paper analysisRead analysis
  14. AttacksarXiv 2610.07645

    SkillPoison:用成功经验投毒自进化 Agent 的技能形成

    提出 SkillPoison,用局部有效的成功经验诱导自进化 Agent 形成过度泛化技能

    Published
    Setting
    AI Agent
    Evaluated models
    deepseek-v4-flash, Qwen V3.8 Flash, GPT-5.5
    AbstractSkillPoison 通过局部有效且验证成功的经验诱导技能过度泛化,在多个评测基准上实现了持久的下游攻击影响。

    SkillPoison 提出了一种针对自进化智能体经验到技能形成过程的攻击范式,通过组织已验证的成功经验诱导技能过度泛化。

    Paper analysisRead analysis
  15. DefensesarXiv 2610.07570

    ProbeGuard:按共识形成过程判断弃答,识别医疗问答中的一致错误

    提出 ProbeGuard,按共识形成过程对医疗问答做选择性弃答

    Published
    Evaluated models
    Qwen3-8B, Llama-3.1-8B-Instruct, HuatuoGPT-o1-8B
    AbstractProbeGuard 用共识形成过程做可认证弃权,并在全票层分开答对与答错的共识。

    ProbeGuard 是给多轮共识医学问答用的认证弃权框架:基板照原样作答,弃权只看共识是怎么形成的。

    Paper analysisRead analysis