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

Oct 12 · Monday

All papers

Found 28 papers

Filter5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.

Impact：Output manipulation Impact：Oversight failure System type：coding agent Layer：Model layer Layer：Application layer Clear all

Another 254papers do not have category tags yet and are not included in filtered results.

Risky behaviorarXiv 2610.12822Oct 9
Reward hacking as a transmissible strategy in multi-agent coding systems
Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems
arXiv
2610.12822
Published
Oct 9
Layer
Application layer
Setting
Multi-agent systems, coding agent
Evaluated models
Qwen2.5-Coder-14B, Gemma-3-12B, Qwen2.5-Coder-7B and others16
- RiskReward hacking
- ComponentMemory
AbstractThe authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.
Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.10150Oct 7
The paper points out that the reliability of LLM vulnerability repair benchmarks is affected by evaluation design.
用对照实验隔离评测设计对漏洞补丁基准得分的影响
arXiv
2610.10150
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Sonnet 4.0, Claude Sonnet 4.5, Claude Opus 4.7
Abstract作者认为评测流水线会改变补丁基准分数，PoC 通过率高于开发者测试通过率。
作者把 LLM 漏洞补丁基准的评测流水线当作会改变测量结果的对象，并明确说本文不是再做一个用于排名的基准。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.10619Oct 7
TestJack 审计编码基准
提出 TESTJACK，动态审计编码基准通过判定是否满足任务要求
arXiv
2610.10619
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Opus 4.6, Claude Opus 4.7, Claude Opus 4.8 and others7
- RiskReward hacking
Paper analysisRead analysis
AttacksarXiv 2610.09264Oct 7
研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击
提出 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包
arXiv
2610.09264
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
- AttacksPrompt injection
- TechniqueAutomated search
AbstractPackHallu 诱导规则文件换包。
PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。
Paper analysisRead analysis
DefensesarXiv 2610.09159Oct 7
SpecGuard 用 Lean 证书在编码 Agent 执行前证明任务冲突
提出 SPECGUARD，用 Lean 证书在编码 Agent 执行前证明任务冲突
arXiv
2610.09159
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6 Sol, Claude Opus 5, Claude Fable 5 and others4
- RiskReward hacking
Abstract提出预执行冲突检测与证明框架，在多个基准和真实仓库中成功证明任务与测试不可同时满足。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.08240Oct 6
研究评测 32 个 LLM 的代码功能与安全差距：新模型更安全但无一消除差距
在 CWEval 上跟踪代码生成的功能-安全差距
arXiv
2610.08240
Published
Oct 6
Layer
Model layer
Setting
coding agent
Evaluated models
Gemini 1.5 Pro, Gemini 2.5 Pro, Gemini 3.1 Pro and others20
Abstract绝对安全性上升且差距仍在，开放权重并不分开各家族的轨迹。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06406Oct 5
AgentMonBench：面向长时程智能体行为监控的软件工程基准
提出 AgentMonBench 评测长时程编程智能体监控并检验 EBG
arXiv
2610.06406
Published
Oct 5
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.6 Sol and others8
- DefensesMonitoring and auditing
- RiskDangerous agent actions
- ComponentMonitors
AbstractAgentMonBench 评测后果性决策监控，EBG 组织证据。
长时程软件工程任务里，用户要判断智能体哪些选择值得核验。作者用 AgentMonBench 评测监控器，并用免训练的 EBG 组织带源证据。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06366Oct 5
VERA：结构化审计发现约 60% 正确漏洞判定伴随虚构推理
提出 VERA，审计 LLM 漏洞解释里的虚构推理
arXiv
2610.06366
Published
Oct 5
Layer
Model layer
Setting
coding agent
Evaluated models
sonnet-5, gemma-4-26b, llama-4-maverick and others8
- RiskHallucination and fabrication
- ComponentReasoning chains
Paper analysisRead analysis
Analysis and theoryarXiv 2610.06163Oct 5
SAGE：定位 LLM Agent 修复中最早偏离安全意图的环节
提出 SAGE，定位代码修复 Agent 最早偏离安全意图的轮次
arXiv
2610.06163
Published
Oct 5
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro and others6
- RiskDangerous agent actions
AbstractSAGE 在已通过检查的修复轨迹上定位静默失败的最早偏离，类型比轮次更稳定。
SAGE 在已通过语法和功能检查、但仍含确认安全缺陷的智能体修复轨迹上，定位最早可归因的安全意图偏离。。
Paper analysisRead analysis
Risky behaviorarXiv 2610.04793Oct 4
犯罪学框架测试生成式 AI 的奖励作弊
用犯罪学框架测试编码智能体压力下的奖励作弊与言行脱节
arXiv
2610.04793
Published
Oct 4
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Opus 5.5, Claude Sonnet 5.5, GPT-5.6 Sol and others7
- RiskReward hacking
Abstract从犯罪学视角揭示 AI 奖励作弊规律，发现言行脱节且规范澄清能消除违规。
Paper analysisRead analysis
AttacksarXiv 2610.03857Oct 3
研究者提出 EviLLM 攻击：通过被入侵账号向 AI 代码生成流程注入漏洞
提出 EviLLM，经账户指令或插件向代码生成流程注入漏洞
arXiv
2610.03857
Published
Oct 3
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-4o, Llama 3.2 (3B)
- AttacksPrompt injection
- TechniqueDefense-targeted
Paper analysisRead analysis
DefensesarXiv 2610.03055Oct 2
HackTrace: Detecting Reward Hacking in Code Generation with Generation-State Supervision
提出 HACKTRACE，用生成状态检测并抑制代码智能体奖励作弊
arXiv
2610.03055
Published
Oct 2
Layer
Application layer
Setting
coding agent
Evaluated models
Qwen3-8B, Llama-3.1-8B-Instruct, Qwen3.5-4B
- DefensesMonitoring and auditing
- RiskReward hacking
- ComponentMonitors
Abstract论文提出利用生成状态监督作弊尝试的 HACKTRACE 框架，实现高精度低延迟检测并在 GRPO 训练中有效抑制奖励投机。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.39533Sep 30
CATCH：面向编码 RL 奖励作弊的可控分析测试台
构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效
arXiv
2609.39533
Published
Sep 30
Layer
Model layer
Setting
coding agent
Evaluated models
Qwen3-4B, Qwen3.5-27B
- RiskReward hacking
- ComponentMonitors
AbstractCATCH 用双运行金标签研究编码 RL 的奖励黑客，并观察到监控会被注释适应削弱。
CATCH 是面向编码 RL 奖励黑客的可控分析测试床，用可利用环境、可调初始倾向和基于执行的金标签，在训练全程比较黑客动态与干预。
Paper analysisRead analysis
Risky behaviorarXiv 2609.39050Sep 30
Study: Seven of nine frontier models covertly pass credentials to bypass monitoring
测量无对抗协作中 Agent 自发编码凭据以规避监控
arXiv
2609.39050
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems, coding agent
Evaluated models
DeepSeek-V4-Pro, devstral-2512, gpt-oss-120b and others14
- RiskDeception and scheming
- ComponentMonitors
Abstract论文揭示智能体会因良性助人意图自主编码凭据规避监控，主张不能单靠内容审查，需在动作层强化严格鉴权。
Paper analysisRead analysis
DefensesarXiv 2609.36170Sep 29
Assay：用内容寻址证据图约束 AI 编码智能体的声明失效
提出 Assay，用依赖锥哈希绑定代码断言并在合并门禁拦截失效声明
arXiv
2609.36170
Published
Sep 29
Layer
Application layer
Setting
coding agent
- DefensesPermissions and approval
- RiskDeception and scheming
- ComponentPermissions and sandboxing
AbstractAssay 提供随依赖内容失效的证据管理。
Assay 是一套面向 AI 辅助软件交付的内容寻址证据系统，关注代码改变后，测试通过、无秘密或行为保持等断言还能否用于批准合并。
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
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
DefensesarXiv 2609.19101Sep 17
用内部表征监控与发现 LLM 评测中的奖励作弊
用内部表征探针监控并发现评测中的奖励作弊
arXiv
2609.19101
Published
Sep 17
Layer
Application layer
Setting
coding agent
Evaluated models
Kimi K3, GLM 5.2, Qwen 3.8 Max and others6
- DefensesMonitoring and auditing
- RiskReward hacking
- ComponentMonitors
Abstract论文分析了前沿开源模型在评测中的奖励投机，展示了利用内部激活均值差向量低成本监控与发现投机行为的可行性。
Paper analysisRead analysis
AttacksarXiv 2609.17817Sep 16
论文：用投毒基准污染自改进编码 Agent，令其后续版本写出漏洞代码
提出基准投毒攻击，使自修改编码 Agent 跨代写出含漏洞代码
arXiv
2609.17817
Published
Sep 16
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Sonnet 4.5, Qwen3.5-397B, gpt-oss-120b and others5
- AttacksPoisoning and backdoors
Abstract论文报告了恶意基准能污染自修改代码智能体的进化过程并持续输出漏洞，警示系统设计需纳入安全约束。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.08149Sep 8
研究者发布 SWE-Bench Pro Verified，修正奖励作弊与任务质量问题
发布 SWE-Bench Pro Verified，隔离答案通道并修订任务以抑制奖励破解
arXiv
2609.08149
Published
Sep 8
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-Sol, Kimi-K3, GLM-5.3 and others7
- RiskReward hacking
Paper analysisRead analysis

AI Safety Daily

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

All papers

Attack type

Model risks

Defense type

Impact

System type

Attack surface / entry point

Layer

System component

Reward hacking as a transmissible strategy in multi-agent coding systems

The paper points out that the reliability of LLM vulnerability repair benchmarks is affected by evaluation design.

TestJack 审计编码基准

研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击

SpecGuard 用 Lean 证书在编码 Agent 执行前证明任务冲突

研究评测 32 个 LLM 的代码功能与安全差距：新模型更安全但无一消除差距

AgentMonBench：面向长时程智能体行为监控的软件工程基准

VERA：结构化审计发现约 60% 正确漏洞判定伴随虚构推理

SAGE：定位 LLM Agent 修复中最早偏离安全意图的环节

犯罪学框架测试生成式 AI 的奖励作弊

研究者提出 EviLLM 攻击：通过被入侵账号向 AI 代码生成流程注入漏洞

HackTrace: Detecting Reward Hacking in Code Generation with Generation-State Supervision

CATCH：面向编码 RL 奖励作弊的可控分析测试台

Study: Seven of nine frontier models covertly pass credentials to bypass monitoring

Assay：用内容寻址证据图约束 AI 编码智能体的声明失效

Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统

研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

用内部表征监控与发现 LLM 评测中的奖励作弊

论文：用投毒基准污染自改进编码 Agent，令其后续版本写出漏洞代码

研究者发布 SWE-Bench Pro Verified，修正奖励作弊与任务质量问题