Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter3

Attack type

Jailbreaks4

Attack technique

Gradient and representation optimization7Automated search27Multi-turn escalation4Encoding and obfuscation21Role-play and persuasion5Reasoning-chain manipulation4Cross-modal payloads11Defense-targeted19Dormant triggers10Selection manipulation3

Defense type

Detection and filtering3

Impact

Harmful content4

System type

Models and APIs4

Attack surface / entry point

User input4

Layer

Prompt layer4

System component

RAG0Guardrails and judges4Vision5Multimodal6
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.
Attack technique：Multi-turn escalationSystem component：RAGSystem component：Guardrails and judgesClear all

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

  1. Evaluation and benchmarksarXiv 2609.36849

    研究评估 GradSafe 在多轮对话中的越狱检测脆弱性

    评测多轮对话中 GradSafe 越狱检测的可分性与脆弱性

    arXiv
    2609.36849
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Llama 3.1 8B Instruct, Qwen2.5-7B-Instruct
    AbstractCWS 显示不安全梯度在真实多轮流量中变弱，且随攻击族和模型而变。

    作者评估梯度越狱检测从单条提示词迁到多轮对话后还剩多少可分性，方法是用 Context Window Scanner 把 GradSafe 原封不动地套到用户轮窗口上。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2606.02630

    MultiTurnPSB

    构建 MultiTurnPSB，评测四轮医疗越狱与分类器输入防御

    arXiv
    2606.02630
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4.1-mini, Claude Sonnet 4.5
    Abstract多轮攻击加剧医疗模型风险，分类器干预有效但受高误报率制约。

    MultiTurnPSB 针对患者端医疗大模型在持续交互中的安全风险，构建了包含三种攻击模态的四轮对抗评测基准。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2603.10068

    ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models

    Using ADVERSA to measure guardrail degradation and reviewer reliability under multi-turn attacks

    arXiv
    2603.10068
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.2
    AbstractADVERSA measures multi-turn guardrail changes using per-turn compliance trajectories and three-reviewer consensus.

    ADVERSA is an automated multi-turn red-teaming measurement framework that records guardrail behavior as per-turn compliance trajectories and simultaneously measures whether reviewers agree. The problem it addresses: single-turn binary pass/fail cannot show how safety properties change under sustained adversarial pressure, nor can it separate gradual refusal consolidation from stable scores. The authors argue that real-world adversaries rewrite and persist over multiple turns.

    Paper analysisRead analysis
You have reached the end