用「稀有区域指纹」精准追踪大模型血统，一篇学术新方法直接看。
arXiv:2505.12682v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly released under restricted licenses, creating a growi…
让AI Agent自动互相攻击，发现生产环境漏洞，这篇论文提出了全新的自动化红队测试框架。
arXiv:2607.11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands,…
提出选择性安全引导方法，通过价值过滤解码提升LLM安全性
arXiv:2605.14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may s…
揭秘大模型安全探针为何在最终token失效：早于最后一层的内部表征已暴露漏洞
arXiv:2605.12726v2 Announce Type: replace Abstract: Final-token safety probes monitor a single hidden state after prompt prefill, but jailbreak prompt…
政府审批AI模型安全标准模糊，专家也摸不清门道，监管迷雾引发行业关注。
"Exactly what that dialog looked like between the government and Anthropic and OpenAI is unclear."
ICML 2026接收：为LLM水印引入功率校准，告别传统启发式调优。
arXiv:2607.05694v1 Announce Type: cross Abstract: Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its e…
大模型在不确定时学会说“不知道”，选择性预测校准方法，提升安全性与可靠性。
arXiv:2607.03528v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as critical decision-making components in hig…
通过截断思维链审计，揭示LLM教育导师是否存在"答案驱动"的推理偏差，提升AI教学可信度。
arXiv:2607.04572v1 Announce Type: new Abstract: Large language model (LLM) tutors often produce fluent step-by-step explanations, but a correct and pe…
论文提出在线安全监控LLM的新方法，引入假设检验框架，为模型部署提供实时风险检测思路。
arXiv:2607.02510v1 Announce Type: new Abstract: Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitor…
最新研究发现，通过模拟审核轨迹可绕过函数调用LLM的安全限制，揭示大模型越狱攻击新路径。
arXiv:2607.00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). W…
发现LLM服务新漏洞：利用特殊Token操纵可越狱在线大模型，揭秘攻击原理与防范思路。
arXiv:2510.10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially cr…
一篇立场论文，直指LLM领域滥用“机器遗忘”术语，引发对模型安全与概念严谨性的反思
arXiv:2606.27379v1 Announce Type: cross Abstract: Large language models increasingly face demands to "forget" training data, knowledge, or behaviors d…
OpenAI官方披露最新大模型GPT-5.6 Sol系统卡，安全部署细节与性能提升一探究竟
System card: https://deploymentsafety.openai.com/gpt-5-6-preview Comments URL: https://news.ycombinator.com/item?id=48689028 Points: 512 # Comments: 3…
利用中间层熵的动态变化检测大模型越狱，为AI安全提供新思路。
arXiv:2606.25182v1 Announce Type: cross Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted p…
从分布偏好角度切入，提出细粒度优化方法解决大模型遗忘问题，视角新颖。
arXiv:2510.04773v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpor…
LLM智能体隐私保护新方案：上下文对齐机制，让AI更懂隐私边界。
arXiv:2606.21710v1 Announce Type: cross Abstract: AI agents acting on behalf of users are constantly making decisions, and for users to trust their ag…
提出基于不确定性的大模型去偏与遗忘新方法，有效解决数据污染问题。
arXiv:2606.23313v1 Announce Type: cross Abstract: Benchmark-based evaluation is the dominant paradigm for assessing large language model (LLM) capabil…
揭露LLM知识编辑的“擦除幻觉”，26页报告揭示技术漏洞，拆解AI修改知识的真实困境。
arXiv:2606.23276v1 Announce Type: cross Abstract: Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly …
论文提出量化与定位LLM对齐失败的新方法，揭示“错误正确”现象，为模型安全提供新视角。
arXiv:2606.18656v1 Announce Type: new Abstract: Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used…
OpenAI新部署模拟器，提前捕获大模型不良行为，让AI安全更可靠
Article URL: https://openai.com/index/deployment-simulation/ Comments URL: https://news.ycombinator.com/item?id=48581468 Points: 1 # Comments: 0