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

Oct 12 · Monday

All papers

Found 14 papers

Filter3

Attack type

Jailbreaks212 Prompt injection14 Poisoning and backdoors9 Model tampering29 Extraction and theft3 Detection evasion15 Malicious use12

Defense type

Detection and filtering3 Monitoring and auditing3

Impact

Harmful content8 Unauthorized actions122 Data and privacy leaks29 Output manipulation63 Availability and reliability5 Oversight failure6

System type

AI Agent10 Multi-agent systems3

Attack surface / entry point

User input12 Tool responses7 Inter-agent messages3

Layer

Application layer10

System component

Guardrails and judges4 Monitors5

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.

Attack type：Prompt injection Impact：Harmful content Impact：Oversight failure Clear all

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

InterpretabilityarXiv 2610.12361Oct 9
Study: legal reasoning models citing legal provisions does not equal relying on legal provisions.
Uses premise permutation and hidden-layer tracing to audit whether legal chain-of-thought truly relies on the cited legal provisions.
arXiv
2610.12361
Published
Oct 9
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-8B, Qwen3-14B, Llama-3.1-8B and others7
- AttacksPrompt injection
- ComponentReasoning chains
AbstractUsing counterfactual substitution of authorities and internal commitment tracing, the authors find that legal CoT rulings depend on authorities only to a limited extent and are vulnerable to prompt injection manipulation.
This study conducts an empirical audit of the causal truthfulness of legal citations in chain-of-thought reasoning of large language models in the legal domain.
Paper analysisRead analysis
AttacksarXiv 2610.09973Oct 7
从期望危害到似然：LLM 智能体越狱的概率重构
提出 OPUR 攻击，用似然梯度优化对抗后缀越狱 LLM 智能体
arXiv
2610.09973
Published
Oct 7
Layer
Application layer
Setting
AI Agent
Attacker
White-box
Evaluated models
Llama-3.1-8B-Instruct, Ministral-8B-Instruct-2410
- AttacksJailbreaks
- TechniqueGradient and representation optimization
Paper analysisRead analysis
DefensesarXiv 2610.08678Oct 7
研究揭示投机解码的安全代价并提出 SecureSD 加固方法
测量有损投机解码的安全代价，并提出 SecureSD 收紧早期验证
arXiv
2610.08678
Published
Oct 7
Layer
Model layer
Setting
AI Agent
Attacker
Black-box
Evaluated models
Qwen3-8B, Qwen3-32B, Llama-3.1-8B-Instruct and others6
- DefensesInference-time intervention
- AttacksJailbreaks
Abstract有损推测解码的早期偏离更快抬高越狱与注入风险。
作者研究有损推测解码在换取速度时，是否会比效用更快地损害越狱与提示注入防护，并给出按位置校正的 SecureSD。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07089Oct 5
研究者提出统一滥用监控基准，覆盖分解攻击与提示注入约 6200 条轨迹
提出危害窗口与区间指标，统一评测分解攻击和提示注入下的智能体滥用监视
arXiv
2610.07089
Published
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
Abstract统一智能体滥用监视框架，动作视角兼顾两类威胁但危害定位仍存瓶颈。
Paper analysisRead analysis
DefensesarXiv 2609.35659Sep 29
Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统
提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改
arXiv
2609.35659
Published
Sep 29
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Code (claude -p, version 2.1), 独立评审（同一 CLI，无工具）
- DefensesMonitoring and auditing
- AttacksPrompt injection
- RiskDangerous agent actions
- ComponentMonitors
AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。
Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.33401Sep 27
论文评估 System One 模型在 Agent 安全决策中的可靠性、校准与选择性自动化
评测 System One 模型对 Agent 安全输入的分类可靠性与校准
arXiv
2609.33401
Published
Sep 27
Layer
Prompt layer
Setting
LLM applications
Evaluated models
Jev 1.13, Laya, English checkpoint, Decider, approximately 2B and others4
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract离线评测表明，安全判定的总体分数和校准不能代替分组误差和带预算的自动决策检查。
Liu 离线评测 System One 模型能否为智能体安全输入给出可自动化的概率决策。问题是分类是否可靠，以及概率能否在指定漏检和误拦上限内支持放行、拦截或复核。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.33102Sep 27
ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架
提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果
arXiv
2609.33102
Published
Sep 27
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5
- AttacksMalicious use
- RiskDeception and scheming
- ComponentMonitors
AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。
Paper analysisRead analysis
Risky behaviorarXiv 2609.30266Sep 25
研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹
测试编程智能体被诱导或自主篡改自身执行轨迹的行为
arXiv
2609.30266
Published
Sep 25
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
- AttacksMalicious use
- RiskDeception and scheming
- ComponentMonitors
Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。
这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.27336Sep 23
CART：面向大语言模型的闭环自适应红队框架
提出闭环自适应红队框架 CART，评测模型与 Agent 的安全失败
arXiv
2609.27336
Published
Sep 23
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Opus 4.8, GPT-5.5, Grok 4.3 and others7
- AttacksPrompt injection
AbstractCART 把红队做成可审计的闭环搜索，在三类评测上比静态回放发现更多失败与更高平均风险。
CART 把自动红队从一次清单式打分，改成带预算、可追溯的闭环搜索。
Paper analysisRead analysis
Analysis and theoryarXiv 2609.23215Sep 20
研究审计 Active Inference Agent 的 LLM 解释器失败模式
审计 Active Inference Agent 上 LLM 解释器的监督叙述失败
arXiv
2609.23215
Published
Sep 20
Layer
Application layer
Setting
LLM applications
Evaluated models
GPT-4o, Claude-3-Opus, Gemini
- AttacksPrompt injection
- RiskMisalignment and value divergence
Abstract三组触发下解释流畅但错误，所提缓解都未被评估。
作者审计的是挂在智能体上的运行时解释器，而不是智能体本身。操作员读到的是信念与动作的自然语言叙述。作者要问哪些可复现触发会让这段叙述失败，以及失败痕迹是什么样。
Paper analysisRead analysis
DefensesarXiv 2609.01046Sep 1
HiveTraceGuard-Pro：面向提示注入、越狱与对抗混淆的紧凑生成式护栏
提出生成式护栏 HiveTraceGuard-Pro，检测提示注入、越狱与混淆
arXiv
2609.01046
Published
Sep 1
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
HiveTraceGuard-Pro (0.6B)
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract0.6B 俄英护栏在自建俄语干净集和 PI-RU 上得分最高，聚合 key 居第三，过阻断和回复精度仍是作者标出的短板。
HiveTraceGuard-Pro 是面向请求与回复审核的 0.6B 生成式护栏，由 Qwen3-0.6B 经 LoRA 微调，在俄语和英语上训练，只输出一个 safe/unsafe 裁决。
Paper analysisRead analysis
DefensesarXiv 2606.08234Jun 6
SciTrace：面向科学发现智能体的轨迹感知安全推理框架
提出 SciTrace，为科学发现智能体加入跨阶段安全推理与工具轨迹核验
arXiv
2606.08234
Published
Jun 6
Layer
Application layer
Setting
science agent, Multi-agent systems
Evaluated models
Llama-3.1-70B-Instruct, Qwen2.5-72B-Instruct, DeepSeek-V3 and others4
- DefensesInference-time intervention
- AttacksPrompt injection
- RiskDangerous capabilities
- ComponentGuardrails and judges
AbstractSciTrace 把安全推理织入科学智能体各阶段，在 SciSafetyBench 上提高安全指标并保持输出质量。
SciTrace 是加在科学发现智能体流水线上的安全框架，不是再在各阶段出口放一个独立过滤器。
Paper analysisRead analysis
AttacksarXiv 2510.09023Oct 10, 2025
Paper proposes adaptive attack framework that breaks through 12 LLM jailbreak and prompt injection defenses
提出自适应攻击框架，击穿越狱与提示注入防御
arXiv
2510.09023
Published
Oct 10, 2025
Layer
Application layer
Setting
AI Agent
Attacker
White-box, Black-box
Evaluated models
Gemini-2.5 Pro, GPT-5 Mini, Llama-3.3 70B and others15
- AttacksJailbreaks
- TechniqueDefense-targeted
Paper analysisRead analysis
DefensesarXiv 2505.23559May 29, 2025
SafeScientist：让 LLM 智能体的科学发现具备风险意识
提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务
arXiv
2505.23559
Published
May 29, 2025
Layer
Application layer
Setting
science agent, Multi-agent systems
Evaluated models
GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
Abstract四层监控加科研安全基准。
SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop