Skip to content

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

Oct 13 · Tuesday

All papers

Found 17 papers

Another 203papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.05894

    研究者提出闭环偏见注入攻击

    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
    Attacker
    Gray-box
    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。

    Paper analysisRead analysis
  2. AttacksarXiv 2610.01062

    Kernelized Activation Steering:将激活引导推广到再生核希尔伯特空间的新框架

    提出核化激活引导 KAS,在推理时自适应转向激活以诱导越狱

    Published
    Evaluated models
    Qwen2.5-7B-Instruct, Gemma-2-9B-IT, Llama-3.1-8B-Instruct and others4
    AbstractKAS 用核梯度做局部自适应转向,并在线性核下恢复 DiM。

    Kernelized Activation Steering(KAS) 把推理时的激活转向写成核空间中的优化,使更新随当前激活相对源、目标参考集的位置而变化。

    Paper analysisRead analysis
  3. AttacksarXiv 2609.39788

    研究:多智能体系统潜在通信链路可被训练用于提升有害顺从

    提出只训练或篡改多智能体潜在通信链路来提高有害遵从

    Published
    Evaluated models
    Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
    Abstract潜在链路本身即可改变冻结智能体系统的安全,奖励既能攻击也能修复。

    学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑:双智能体、三级顺序协作,以及双专家加汇总。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.27542

    Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

    提出控制标记注入,清空工具 Agent 的思维链以绕过推理监控

    Published
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过,且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  5. AttacksarXiv 2608.07430

    研究者提出 SN-Guided Diffusion,利用扩散大模型安全神经元实现离线越狱

    提出 SN-Guided Diffusion,利用安全神经元实现离线越狱

    Published
    Evaluated models
    Qwen2.5-7B-Instruct, LLaDA-8B-Instruct, Dream-Instruct-7B and others15
    Abstract论文揭示了扩散语言模型对自回归安全神经元的继承性,并提出纯离线黑盒越狱框架 SN-Guided Diffusion。

    论文系统评估了扩散大语言模型(DLLM)在安全对齐中的双重角色——既作为白盒攻击目标,又作为黑盒越狱生成的对抗工具。

    Paper analysisRead analysis
  6. AttacksarXiv 2606.12716

    PaperGuard:针对多模态 AI 同行评审的攻击与防御基准

    提出 PaperGuard,用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令

    Published
    Evaluated models
    Claude-sonnet-4.5, GPT-4o, GPT-4.1 and others11
    AbstractPaperGuard 测到提示注入与白盒视觉抬分,并比较分块检索防御。

    PaperGuard同时评测并检测多模态 AI 审稿中的评分操纵。

    Paper analysisRead analysis
  7. AttacksarXiv 2605.24421

    研究者提出日志型提示注入攻击,可抑制 SOC 中 LLM 分析助手的恶意日志识别

    提出日志基底提示注入,操纵 SOC 分析员的分类、摘要与处置建议

    Published
    Evaluated models
    gpt-4o-mini

    Abstract在 gpt-4o-mini 上,人格劫持与上下文操纵可改写 SOC 分析输出,直接覆盖在分类上无效。

    Paper analysisRead analysis
  8. AttacksarXiv 2605.08513

    Apple 研究者发现抑制单个神经元即可绕过 LLM 安全对齐

    提出单神经元激活干预,抑制拒答神经元或放大概念神经元以绕过安全对齐

    Published
    Attacker
    White-box
    Evaluated models
    Qwen3-1.7B, Qwen3-4B, Qwen3-8B and others11

    Abstract作者称大模型安全由拒答门控与概念底座构成,干预单个神经元足以双向击穿对齐,且拒答神经元在预训练阶段已然存在。

    Paper analysisRead analysis
  9. AttacksarXiv 2602.17837

    TFL: Targeted Bit-Flip Attack against Large Language Models

    Proposes TFL targeted bit flipping so that selected prompts output false answers while unrelated queries remain correct

    Published
    Evaluated models
    Qwen3-8B, DeepSeek-R1-Distill-Qwen-14B, LLaMA-3.1-8B-INSTRUCT
    AbstractTFL 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.

    Paper analysisRead analysis
  10. AttacksarXiv 2602.05444

    Causal front-door adjustment for robust jailbreak attacks on LLMs

    Proposes CFA2, using SAE to locate defense directions and orthogonalizing output weights to achieve jailbreak

    Published
    Attacker
    White-box
    Evaluated models
    Llama 3.1 8B Instruct, Llama2 7B Chat, Mistral 7B Instruct and others4
    Paper analysisRead analysis
  11. AttacksarXiv 2602.00364

    "Someone hid it": Query-agnostic black-box attacks against LLM retrieval

    提出查询无关黑盒攻击 DQ-A,用可迁移文末后缀降低文档检索排名

    Published
    Evaluated models
    Qwen-1.5-7B-Instruct, SFR-Embedding-Mistral, E5-Mistral-7B-Instruct and others10
    AbstractDQ-A 以无查询黑盒后缀压低 LLM 检索排名,并在 BRIGHT 上比较三种基线。

    DQ-A 是一种 query-agnostic、complete black-box 的文档隐藏攻击,对象是用最后隐层相似度匹配的 LLM 检索。

    Paper analysisRead analysis
  12. AttacksarXiv 2601.20283

    One word is enough: Minimal adversarial perturbations for neural text ranking

    提出查询中心词的单次插入或替换攻击,操纵神经排序名次

    Published
    Evaluated models
    BERT-base-mdoc-BM25, monoT5-base-MSMARCO
    Abstract作者称单词扰动即可抬升名次、中段文档最脆弱,且比白盒 PRADA 更少编辑。

    单个与查询对齐的词,就可能改掉神经重排结果。要做的是少改原文,仍把目标文档在 NRM 列表里的名次抬高。

    Paper analysisRead analysis
You have reached the end