Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.

Attack type：Detection evasion System type：LLM applications System type：coding agent System type：web agent System type：Browser and computer use System type：Embodied systems and robotics Clear all

Another 215papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12292Oct 9
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
arXiv
2610.12292
Published
Oct 9
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
LAYA-TD, LAYA-EN, LAYA-ML and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
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
AttacksarXiv 2610.10742Oct 8
BRANCH 方法绕过 6 套多扫描器护栏系统
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
arXiv
2610.10742
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Meta Llama Guard 3 8B, Meta Llama Guard 7B, Meta Llama Guard 3 1B and others18
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2610.10612Oct 7
PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器
提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器
arXiv
2610.10612
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
CISCO, HSS, AUDITOR and others8
- DefensesDetection and filtering
- AttacksDetection evasion
- TechniqueDefense-targeted
- ComponentMCP and skills
Abstract论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。
这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。
Paper analysisRead analysis
DefensesarXiv 2610.05870Oct 5
MBZUAI 提出可校准的真实图像认证方法
提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动
arXiv
2610.05870
Published
Oct 5
Layer
Application layer
Setting
LLM applications
Attacker
White-box
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentImage generation
Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。
Paper analysisRead analysis
DefensesarXiv 2610.02432Oct 2
论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护
提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感
arXiv
2610.02432
Published
Oct 2
Layer
Application layer
Setting
LLM applications, AI Agent
Attacker
Black-box
Evaluated models
Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2609.29130Sep 24
ClaimMirage：域名中的自我声明如何改变 LLM 威胁判断
提出 ClaimMirage，以域名自述声称改变 LLM 威胁告警判断
arXiv
2609.29130
Published
Sep 24
Layer
Application layer
Setting
LLM applications
Evaluated models
Llama 3.3 70B Instruct-Turbo, Gemma 3 4B it, Gemma 3 12B it and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract作者称自述声称可增减告警。
Paper analysisRead analysis
AttacksarXiv 2609.19722Sep 17
ALIBI：向二进制注入虚假安全叙事可让 LLM 恶意软件分析器误判
提出 ALIBI，向恶意二进制注入不执行掩护叙事使分析器误判为良性
arXiv
2609.19722
Published
Sep 17
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Gemini 2.5 Pro, GPT-5.5 Pro, Claude Opus 4.7
- AttacksDetection evasion
- TechniqueRole-play and persuasion
AbstractALIBI 用二进制内的掩护叙事重释可疑静态证据，Gemini 上翻转多，另两模型主要为降级。
ALIBI 是针对 LLM 恶意软件分诊的语义掩护叙事攻击：不覆盖系统指令，而把仍可见的可疑静态证据重释成良性安全产品的预期行为。
Paper analysisRead analysis
DefensesarXiv 2609.08394Sep 8
Windows 恶意软件检测器作为复合 AI 系统：准确率、效率与对抗鲁棒性的权衡
提出 OBELISK 三级流水线，权衡恶意软件检测的准确率、开销与鲁棒性
arXiv
2609.08394
Published
Sep 8
Layer
Application layer
Setting
LLM applications
Attacker
White-box, Black-box
Evaluated models
GBDT-ALL, GBDT-YARA, NEBULA-ALL and others4
- DefensesDetection and filtering
- AttacksDetection evasion
Abstract三级过滤以不大的检测损失换速度，同一机制扩大攻击面，部署应按约束选配置。
OBELISK 把 Windows PE 恶意软件检测做成 YARA、EMBER-GBDT 与 Nebula 的顺序流水线，用来同时看检出、计算开销和对抗鲁棒性。
Paper analysisRead analysis
AttacksarXiv 2608.09732Aug 10
ColluSkill 用跨技能组合绕过 Agent 技能扫描器
提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器
arXiv
2608.09732
Published
Aug 10
Layer
Application layer
Setting
coding agent
Attacker
Black-box, Gray-box
Evaluated models
GPT-5.5, DeepSeek-V4-Pro, GLM-5.2
- DefensesDetection and filtering
- AttacksDetection evasion
- TechniqueDefense-targeted
- ComponentMCP and skills
Abstract论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
Paper analysisRead analysis
DefensesarXiv 2608.06422Aug 6
CMU 研究：分片判断可避免 LLM 监督失效并抵御对抗利用
提出分片监督，将评判标准分配给独立调用以抵御展示攻击
arXiv
2608.06422
Published
Aug 6
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Claude Opus 4.8, Claude Sonnet 4.6, Claude Opus 4.6 and others4
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract论文揭示决策负载是大模型监督的独立瓶颈，提出分片与辩论机制有效分离注意力与平衡证据，在多项高难度基准上实现稳健评判。
本文系统研究了大语言模型在执行多标准监督与评判时的决策负载瓶颈及其安全风险。
Paper analysisRead analysis
DefensesarXiv 2608.12361Jul 5
基于搜索增强 LLM 的中文新词毒性共识检测框架 SeTox
提出 SeTox 检索增强框架，检测中文新词的隐性毒性
arXiv
2608.12361
Published
Jul 5
Layer
Application layer
Setting
LLM applications
Evaluated models
SeTox-Qwen2.5-7B
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractSeTox 用检索把公共共识接入静态 LLM，以检测中文毒性新词。
SeTox 研究中文新词上的隐性毒性检测：词表加检索增强，使静态 LLM 在不重训练的情况下利用公开网页上下文。
Paper analysisRead analysis
AttacksarXiv 2606.09700Jun 9
The researchers propose the HPAA attack: bypassing 13 content moderation systems with typographic visual cues
提出 HPAA 攻击，用排版视觉线索绕过内容审核系统
arXiv
2606.09700
Published
Jun 9
Layer
Prompt layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Llama-Guard-3-8B, Perspective API, ShieldGemma-2B and others13
- AttacksDetection evasion
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Abstract揭示了排版视觉线索与分词差异带来的审核盲区，HPAA 以极低查询实现近乎完全规避。
这篇论文研究了人类视觉感知与大模型分词处理机制之间的差异所导致的内容审核漏洞。
Paper analysisRead analysis
AttacksarXiv 2605.26156May 24
BITE：用上下文赌博机操纵风格偏置攻击 LLM 评委
提出 BITE，用上下文赌博机选择风格修改抬高 LLM 评委打分
arXiv
2605.26156
Published
May 24
Layer
Prompt layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
o3-mini, Gemini-2.5-Flash, Llama-3.3-70B-Instruct and others8
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentGuardrails and judges
AbstractBITE 用黑盒赌博机利用风格偏差抬分，作者称这对 LLM-as-a-judge 构成威胁。
BITE 是黑盒风格操纵：在保持答案语义的同时，抬高 LLM 评审给出的分数。
Paper analysisRead analysis
AttacksarXiv 2605.22258May 21
CITA：面向中文隐式毒性的攻击与防御数据生成框架
提出 CITA 三阶段框架，生成可绕过毒性检测器的中文隐式毒性文本
arXiv
2605.22258
Published
May 21
Layer
Application layer
Setting
LLM applications
Evaluated models
Tencent, Baidu, Gemini 3.1 Pro and others11
- AttacksDetection evasion
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2602.13576Feb 14
Rubrics as an attack surface: covert preference drift in LLM judges
提出改评分标准的搜索攻击，使 LLM 评判者在基准达标下发生偏好漂移
arXiv
2602.13576
Published
Feb 14
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Qwen3-14B, Gemma-3-27B-it, DeepSeek-V3 and others8
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentGuardrails and judges
AbstractRIPD 指 benchmark 合规的 rubric 修改仍可使 judge 偏好在 target 域定向漂移，并经 DPO 传入策略。
作者把自然语言 rubric 视为 LLM judge 的可编辑控制接口，并称只靠 benchmark 验证不足以稳住 target 域偏好。
Paper analysisRead analysis
AttacksarXiv 2602.05484Feb 5
Masked Mirror: Covert Prompt Injection Attacks Against LLM-Based Phishing Detection
提出隐蔽提示注入攻击 LLM 钓鱼检测器，并给出防御 InjectDefuser
arXiv
2602.05484
Published
Feb 5
Layer
Application layer
Setting
LLM applications
Evaluated models
OpenAI GPT-5, xAI Grok 4 Fast (Non-Reasoning), Meta Llama 4 Maverick and others4
- DefensesInstruction–data separation
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2602.00979Feb 1
GradingAttack: Revealing Security Vulnerabilities in LLM-Based Educational Grading Agents
提出 GradingAttack，用梯度后缀与角色扮演操纵教育评分智能体判定
arXiv
2602.00979
Published
Feb 1
Layer
Application layer
Setting
LLM applications
Evaluated models
Qwen2.5-7B, Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct and others8
- AttacksDetection evasion
- TechniqueGradient and representation optimization
Paper analysisRead analysis
AttacksarXiv 2602.02569Jan 31
DECEIVE-AFC：针对检索式 LLM 事实核查系统的对抗性主张攻击
提出 DECEIVE-AFC，以声明改写诱导搜索增强事实核查误判
arXiv
2602.02569
Published
Jan 31
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
HiSS, LEMMA, DEFAME and others4
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentRAG
Paper analysisRead analysis
DefensesarXiv 2601.19051Jan 27
Proactively hardening LLM defenses with HASTE
提出 HASTE，挖掘 hard negative 再训练恶意提示检测器
arXiv
2601.19051
Published
Jan 27
Layer
Prompt layer
Setting
LLM applications
Evaluated models
protectai/deberta-v3-base-prompt-injection
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractHASTE 用 hard negative 再训练检测器。
HASTE 是检测器侧的闭环硬化框架：持续构造能绕过当前检测的对抗提示，再用来更新恶意提示分类器。
Paper analysisRead analysis
AttacksarXiv 2505.23266May 29, 2025
AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体
提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知
arXiv
2505.23266
Published
May 29, 2025
Layer
Application layer
Setting
Embodied systems and robotics
Attacker
White-box
Evaluated models
Lseg, Clip, ViT-L/16 and others5
- AttacksDetection evasion
- TechniqueGradient and representation optimization
- ComponentVision
AbstractAdvOF 以多视角融合生成对抗物体。
AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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