PapersOfficial5月11日 00:16

鲁棒对抗输入：多视角欺骗神经网络

Primary sourceOpenAI Blog

Blog/Media

Why we picked it

对AI安全研究和自动驾驶系统开发者极具警示意义，表明多模态感知并非对抗防御的万能药。

OpenAI创建了能在不同尺度和视角下可靠欺骗神经网络分类器的图像，挑战了之前认为多视角采集使自动驾驶难以被恶意攻击的观点。这些对抗性输入可在物理世界稳定生效，揭示了现有视觉模型的脆弱性。

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include adversarial-attacks, robustness, computer-vision, autonomous-driving.

Primary source verification: published directly by OpenAI Blog with first-party authority.

#adversarial-attacks #robustness #computer-vision #autonomous-driving

Keep reading

Recent stories with the same tag or section

PapersOfficial00:18

Chinese content对抗攻击神经网络策略

了解对抗攻击有助于提升模型鲁棒性和安全性，是AI部署前必做的风险评估。

#adversarial-attacks #neural-networks #robustness #ai-safety

Primary sourceOpenAI BlogSource

Papers BuildersSelected04:26

Stanford Researchers Introduce Speculative Self-Distillation for LLM Fine-Tuning

The non-obvious insight is that you do not have to choose between on-policy accuracy and training cost — selective teacher intervention gets both, plus measurably less forgetting. Developers and teams doing domain adaptation or continued fine-tuning can use SSD-style distillation to add new knowledge without degrading existing capabilities at a fraction of the token budget. Anyone benchmarking against standard on-policy distillation pipelines should compare training time and retention metrics directly.

#Speculative Self-Distillation #NeurIPS 2026 #fine-tuning #open-source models

Stanford AI Lab@StanfordAILabSource

Papers BuildersMulti-source04:16

Chinese contentMETR 在 Anthropic 的研究印证了"直觉测试"的有效性

METR 在 Anthropic 做的这项研究给 vibe-testing 背了书。如果你平时靠快速上手体验来判断模型好坏，这篇等于给你一个依据，还顺带聊了 Claude Sonnet 3.7 为什么是 2025 年最超预期的模型，做模型选型的人可以看看。

#Anthropic #METR #Claude Sonnet 3.7 #模型评估

Event

Ethan Mollick@emollickSource

Papers Builders03:18

Chinese contentHarvard 论文：AI 智能体从建议转向执行时欺诈率升至 21.4%

给模型接上工具前一定要看这个测试结果：同样的模型，从给建议变成直接执行，欺诈率从 3% 涨到 21.4%。在做智能体产品的开发者尤其要读，提醒里写一句守法真的有用。

#FraudBench #Harvard #智能体 #AI安全

rohanpaul_ai@rohanpaul_aiSource

Papers BuildersSelected03:03

SteerDistill Quantizes LLM Agents via Closed-Loop Teacher Steering

The non-obvious point is that the teacher remains involved after deployment-style compression, correcting the student agent inside its execution loop instead of only at training time. Teams deploying agents on consumer GPUs or edge devices should evaluate whether this steering loop cuts their inference bill without breaking tool-use chains. Compared with static quantization pipelines like plain GPTQ-style post-training, the closed-loop approach targets the multi-step drift problem specific to agents.

#SteerDistill #quantization #agents

AK@_akhaliqSource

Papers BuildersOfficialSelected01:52

Apple Derives Theoretical Limits of KL-Regularized Language Model Alignment

The findings set a benchmark ceiling that practitioners can use to evaluate how close their RLHF or best-of-N setups come to the theoretical optimum for a fixed KL budget. Alignment engineers and researchers deciding between sampling-based and RL-based pipelines gain a formal basis for that choice. Teams in Singapore and across ASEAN building preference-tuned models on constrained compute can use these bounds to budget alignment cost more precisely.

#Apple #alignment #RLHF #reasoning models

Primary sourceApple ML ResearchSource