Another 227papers do not have category tags yet and are not included in filtered results.
Propose X-AgentRed, which uses a tool dependency graph to red-team cross-service unauthorized harm in personal agents
Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel
The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
Uses premise permutation and hidden-layer tracing to audit whether legal chain-of-thought truly relies on the cited legal provisions.
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.
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
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.
Proposes ReSI, which recursively improves model safety alignment using automatic red teaming and recipe search.
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.
提出 IRIS，用意图恢复率区分遮蔽越狱下无害输出的原因
IRIS 把意图恢复当作中间信号，用来解释意图遮蔽提示下为何没有出现有害协助。
构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据
EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。
Retest and extend prompt injection against AI agents, and use Agent Card deception to manipulate A2A selection
The authors retested prompt injection on their own LangChain, AutoGen, and A2A systems, and modified the Agent Card to see if choices shifted. The abstract states the experiments mainly highlight single-agent weaknesses while extending attacks to multi-agent.
提出 GUISE 基准与 AXIS 训练，防御叙事包装越狱
作者测量叙事包装下的拒答失效，并训练一个在未见包装上拒绝、同时仍回答同风格良性请求的适配器。问题是：安全对齐模型拒绝直说的有害请求，却回答嵌进角色或叙事里的同一请求。文言文被用来把语域和包装拆开。
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
提出零空间激活引导 Nullify，免训练擦除指定记忆并保持效用
提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤
Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。
提出 OPUR 攻击，用似然梯度优化对抗后缀越狱 LLM 智能体
提出 AgentTracer，事后定位间接提示注入的注入点并重建攻击链
提出 SafeBridge，对齐循环语言模型不同循环深度的安全性
提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链
这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。
提出 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱
这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。