Skip to content

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

Oct 12 · Monday

All papers

Found 217 papers
Filter2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.

Another 265papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. AttacksarXiv 2610.12292

    The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

    Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations

    Published
    Attacker
    Black-box
    Evaluated models
    LAYA-TD, LAYA-EN, LAYA-ML and others5

    AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.

    Paper analysisRead analysis
  3. AttacksarXiv 2610.11932

    A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text

    Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.

    Published
    Evaluated models
    Grok, Doubao, ChatGPT and others10

    AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.

    Paper analysisRead analysis
  4. AttacksarXiv 2610.11112

    EpiReal-Bench:商用图像生成模型虚假声明红队基准

    构建 EpiReal-Bench,评测图像生成器将虚假主张渲染为可信证据

    Published
    Attacker
    Black-box
    Evaluated models
    GPT-Image-2, Nano Banana 2, Grok Imagen 2.0 and others4
    Abstract四款商用图像模型能把假主张画成可信证据。

    EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。

    Paper analysisRead analysis
  5. AttacksarXiv 2610.12524

    An exploration of attacks on AI agent systems

    重测并扩展对 AI Agent 的提示注入,并用 Agent Card 欺骗操纵 A2A 选择

    Published
    Setting
    AI Agent
    Evaluated models
    Ollama Mistral 0.9.5, llama3-8b-8192, gemini-2.0-flash-lite and others5
    Abstract单智能体过滤与分类可被格式或措辞绕过,A2A 选卡还会偏向名称和描述。

    作者在自建的 LangChain、AutoGen 和 A2A 系统上重测提示注入,并改 Agent Card 看选择是否偏移。摘要称试验主要凸显单智能体弱点,同时把攻击扩到多智能体。

    Paper analysisRead analysis
  6. AttacksarXiv 2610.09027

    P-VMI:对抗图像经 KV cache 持续影响多轮对话

    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
    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。

    Paper analysisRead analysis
  7. 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
  8. AttacksarXiv 2610.06670

    研究者提出 Reward Stealing Attack,从对齐模型行为反推安全奖励实施攻击

    提出 ReSA,从对齐模型行为恢复安全奖励并在解码时反转

    Published
    Evaluated models
    Llama3.1-8B-Instruct, Gemma-7B-Instruct, Qwen2.5-7B-Instruct and others9
    AbstractReSA 用最大熵 IRL 从对齐模型行为恢复代理安全奖励,并在解码时反转以诱导有害输出。

    ReSA 是一种对抗攻击:从对齐模型的可观察行为恢复代理安全奖励,再在解码时把该奖励反过来用。。

    Paper analysisRead analysis
  9. AttacksarXiv 2610.06093

    研究评测训练数据提取风险的跨语言迁移

    用翻译前缀做跨语言训练数据提取,恢复英语训练文本中的 PII

    Published
    Evaluated models
    GPT-Neo 1.3B, GPT-Neo 2.7B, GPT-J 6B and others7
    Abstract跨语言 TDE 能恢复英语记忆的 PII,转移随多语训练和措辞保真变化。

    这篇工作检验训练数据抽取是否跨语言:英语段落里记住的 PII,能否被其他语言的前缀逐字抽出。

    Paper analysisRead analysis
  10. AttacksarXiv 2610.05943

    CRIME 框架利用良性 Agent 技能组合诱发恶意行为

    提出 CRIME 框架,组合良性 Agent 技能诱发恶意行为

    Published
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
    Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果,单独审查对不上。

    CRIME 把公共技能库中各自通过审查的技能配成两两组合,看联合执行能否实现指定恶意任务。。

    Paper analysisRead analysis
  11. AttacksarXiv 2610.05346

    研究者提出序列马赛克攻击并给出防御理论

    形式化 watchman 防御以阻止序贯马赛克攻击

    Published
    Evaluated models
    Qwen3.6-35B-A3B, Gemma-4-26B-A4B-it, DeepSeek-V2-Lite (16B-A2.4B)
    Abstractwatchman 理论给出零失败且有用的条件。

    这篇工作同时给出序贯马赛克防御的博弈理论,以及冻结 LLM 上的分角色自博弈训练。

    Paper analysisRead analysis
  12. AttacksarXiv 2610.04985

    研究揭示 Jev 作为应用决策层的安全与隐私风险

    评估应用决策层的输入注入与隐私推断风险

    Published
    Evaluated models
    Jev, NanoJev
    AbstractJev 的类型化决策可被输入与训练操纵,也会泄露信息,并同时支持检测与滥用。

    Jev 是 TypeSafe 的 System One 模型,把应用 state 和固定问题变成 Choice、Noul 或 Score 的类型化决策与概率。作者用官方 API 和可改训练的 NanoJev,考察它作为决策层时的操纵、泄露与双重用途。

    Paper analysisRead analysis
  13. AttacksarXiv 2610.04589

    StegoMemory red team testing: agent persistent memory can be used as a cross-session covert channel

    提出 StegoMemory,评测智能体持久记忆作为跨会话隐写信道

    Published
    Setting
    AI Agent
    Evaluated models
    Llama 3.1 405B, Claude 3.5 Sonnet, GPT-4o and others13

    Abstract研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密,写入持久化是主要防御瓶颈,呼吁建立记忆完整性防御。

    Paper analysisRead analysis
  14. AttacksarXiv 2610.03430

    JIL:通过对抗后缀操纵 LLM 请求调度优先级

    提出 JIL 对抗后缀,压低长度预测以抬高请求调度优先级

    Published
    Evaluated models
    Llama-3-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3 and others4
    AbstractJIL 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。

    Paper analysisRead analysis