Another 215papers do not have category tags yet and are not included in filtered results.
Proposes SWE-DeceptionBench to evaluate LLM deception in the software development lifecycle
Auditing training labels for label-only backdoors, comparing spaces and statistics, and judging by retraining
The authors ask: can a defender without trusted data decide which training labels to keep, and how much clean data this destroys, and what the final model accuracy is.
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.
Proposes the ISE framework to evaluate the epistemic humility of LLM agents under knowledge conflicts
What the authors want to test is not whether the agent's final answer is correct, but whether, when a knowledge conflict arises, it recognizes the gap in its trajectory, performs bounded tool follow-up, and writes the unresolved uncertainty to the user.
Diagnose whether compliance system rulings change with perturbations to regulatory rules
Use behavioral counterfactuals and activation probes to audit whether compliance rulings rely on the given rules. The authors aim to separate two kinds of seemingly identical correct rulings: those that use the given rules, and those obtained from case surface features or training patterns.
Analyzing why optimizing teaching adaptation metrics collapses tutoring choices and diverges from expert judgment
After turning teaching adaptation metrics into a fine-tuning objective, the metrics rise while scores from trained educators decline.
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
提出义务识别基准 ObligationBench，并训练护栏识别 Agent 未履行的安全义务
作者认为编码智能体的安全不能只靠拦截禁止动作，还要找出终止时仍未做的安全关键动作，并将其称为义务。
构建 Workerville 基准，测量组织条件如何改变 Agent 的安全行为
Workerville 用组织行为测量智能体安全如何随监督、同伴和记忆条件变化。。要处理的缺口是：持续运行的 LLM 智能体同时接收用户指令、同伴消息和长期记忆，但既有安全评测多把这些通道拆开，没有统一的定量测量。
提出 SSCBench，评测工具调用 Agent 故障注入测试的证据有效性
SSCBench 研究工具使用智能体的故障注入结果，在什么证据条件下可以被解释。
提出 RL-ARC，用推理置信度在强化学习中校准推理模型
RL-ARC 是校准感知的强化学习框架，用推理过程的口头置信度调节答案置信度。
用 BeliefScope 分离固定命题上证据与压力对模型信念的影响
BeliefScope 是一个黑盒行为诊断框架，用来把固定命题上的回答变化拆成证据驱动的修正，和不加新事实的方向性压力。信念修正评测能看到信息基础变化后的更新，谄媚评测能看到用户影响下的顺从或漂移。作者认为，当两种输入都偏向同一结论时，表面偏移本身不能区分来源。
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.
提出零空间激活引导 Nullify，免训练擦除指定记忆并保持效用
比较连续后训练阶段如何改变语言模型的说服力
作者用同一人类协议，把 LLM 说服力拆成阴谋数据上的失调 SFT、说服数据上的 SFT，以及其后的 IPO。
提出 OrthoPurify，用正交投影清除视觉语言模型适配器中的劫持方向
OrthoPurify 是部署前的 LVLM 后门净化方法，用一次正交投影去掉被劫持的权重更新方向。
提出利用祖先 VLM 优化对抗补丁，使已部署 VLA 任务失败
评测 LLM 审计 Agent 日志时来源重建是否有证据支持
包级审计检查保存的智能体动作里，哪些来源结论能被交给分析者的记录支持。
提出 SOUL 稀疏特征策略遗忘，缓解 VLA 状态幻觉
SOUL用稀疏特征引导的策略 unlearning 处理 VLA 的 state hallucination。