Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Impact

Unauthorized actions7Data and privacy leaks2Output manipulation5Availability and reliability0

Attack surface / entry point

User input4Tool responses2Memory writes9

System component

Memory2Permissions and sandboxing3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Impact：Data and privacy leaksImpact：Availability and reliabilityAttack surface / entry point：Tool responsesSystem component：MemoryClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.04875

    Forgetting without restart: execution-state forgetting for stateful LLM agents

    Proposes execution-state forgetting, using provenance-guided selective replay to purify stateful agents

    arXiv
    2609.04875
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractSelective replay concatenates the clean prefix with the sanitized suffix, and main-table metrics match full reset.

    This work defines forgetting in long-horizon agents as runtime counterfactual equivalence, rather than deleting a plaintext memory.

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2605.01970

    Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses on LLM Agents

    构建 Trojan Hippo Bench，评测 Agent 持久记忆投毒与外泄

    arXiv
    2605.01970
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemini 3.1 Pro, GPT-5-mini, GPT-5

    Abstract论文提出了评测智能体持久化记忆攻击与防御的 Trojan Hippo Bench，揭示了潜伏攻击威胁及内存防御的安全与效用权衡。

    Paper analysisRead analysis
You have reached the end