THE ML ENGINEER · TOPIC ARCHIVE

Newsletter issues on ML security

Newsletter home

#400Aug 2026Production ML Across 2015-2035, Zalando on Agentic Engineering at Scale, Stealing Reasoning from Encrypted Traces, Hugging Face on Open Models, Cloudflare on MCP Traffic Control + more 🚀llms · ai-agents · ml-security #399Aug 2026The New Institute for AI, Multi-Tenant Multi-Tier Memory for AI Agents, LLMs Reward Expertise, Qwen3.8-Max and Open Weights, Harness Design for Long-Running Apps, Mistral's Shieldstral Safety Classifier + more 🚀llms · ai-agents · ml-security #398Aug 2026OpenAI Hugging Face Hack Timeline, Cheating in Frontier Model Evaluations, Kimi K3 Architecture, Netflix LLM-Native Recommendations, OpenAI Mathematics Advances + more 🚀ml-security · llms · recommender-systems #397Jul 2026Europe Launches APERTUS 1.5, Why Software Factories Fail, OpenAI + Hugging Face Security Post-Mortem, Opus 5 Context Engineering, DuckDB Internals Part II + more 🚀llms · ml-security · data-engineering #394Jul 2026Stanford Study on Local LLMs, Snorkel's Senior SWE-Bench, Google DeepMind's Tabular Foundation Model, Performance Per Dollar Improving, CVEs Spike After Mythos Release + more 🚀ai-agents · llms · ml-security #387May 2026Toto 2.0 Time Series Foundation Model, TabPFN-3 Tabular Foundation Models, Stanford SWE Real-World Dataset, DeepMind AlphaEvolve Scaling Impact, Mozilla on Mithos Vulnerabilities + more 🚀forecasting · ai-agents · ml-security #385May 2026Demis Hassabis: Agents & AGI, Google Cloud MCP Ecosystem, Netflix State of ML Serving, PyTorch Lightning Supply Attack, Multi-Modal Traces in MLFlow + more 🚀ml-security · ai-agents · mlops #382Apr 2026Releasing KAOS v0.4.1!, Come Say Hi @ PyCon DE!, KAOS Autonomous Extension, Anthropic Tackling Security Risks, How People Use ChatGPT, Linus Torvalds Agentic Guidelines + more 🚀ai-agents · ml-security · ml-research #378Mar 2026The State of Data Agents, Agentic Engineering Quality, Scaling Python Performance, Hacking McKinsey's Platform, DuckDB Benchmarks in Macbook Neo + more 🚀ai-agents · ml-security #363Dec 2025Black Forest Labs Launches FLUX-2, Major Supply Chain Attacks, Raschka on Building an LLM, 2025 Advent of Code + more 🚀generative-ai · ml-security · llms #361Nov 2025Stanford CS236: Deep Generative Models, Introducing the OWASP Top 10 2025, GenAI World Foundation Models, Synthetic Time Series Foundation Models + more 🚀generative-ai · ml-security · forecasting #356Oct 2025A History of Large Language Models, Few Samples Break LLMs, Uber Michelangelo in 2025, Companies Measure AI Productivity + more 🚀llms · ml-security · mlops #352Sept 2025Hierarchical Reasoning Models, QWEN3 Towards Efficiency, Multi-Agents for CVE Exploits, Simon Willison Vibe Code Apps + more 🚀llms · mlops · ml-security #348Aug 2025LeadDev AI Impact Report, MCP Vulnerabilities For Every Dev, Architecting Large Software Sys, Machine Learning Visualised, Best Practice for Agentic Systems + more 🚀ml-security · ai-agents · ml-education #341Jun 2025Internals of vLLM Inference, Databricks Unified ML Governance, A Deep Dive Into TPUs, Google MultiModal Released, LLM Transformers as Malware + more 🚀mlops · ai-policy · ml-security #317Jan 2025Chip Huyen on Agentic AI, 10y Review of Anomaly Detection, Modular SVGs with GenAI Models, Efficient Coding with LLMs, Extracting AI models from Apps + more 🚀ai-agents · llms · ml-security #292Jul 2024AI & Machine Learning Security, Goldman on GenAI Value Gap, Yoshua Bengio on AI Safety, The Future of AI in Engineering + more 🚀ml-security #279Apr 2024Stanford State of AI Report, Stripe Feature Store Airbnb OSS, NSA Security Framework for AI, LLMs as Effective Regressors, Llama 3 Latest META's Release + more 🚀llms · ml-security #260Dec 2023Practical Deep Learning FastAI, AI Generating Triangle Meshes, Extracting Data from ChatGPT, Stable Difussion Visual Anagrams, Designing Distributed SQL Engine + more 🚀ml-security · generative-ai · ml-education #239Jul 2023Awesome Prod ML 5y & 14k ⭐, Stackoverflow on ML Ecosystem, Poisoning LLMs to Spread Misinfo, Survey on LLM Evaluations, Keras 3.0 on JAX, PyTorch & TF + more 🚀ml-security · llms #236Jun 2023The State of Production ML 2023, Economic Potential of Gen AI, Playing with Steamlit & LLMs, MITRE ML Security Mitigations, A/B Testing Problems & Learnings + more 🚀mlops · generative-ai · ml-security #235Jun 2023Machine Learning Security at NeurIPS, Google's Secure AI Framework, AI Fairness Across Linkedin, META's AI Music Generation, How Google Manages Tech Debt + more 🚀ml-security · ai-ethics · generative-ai #234Jun 2023OWASP Top 10 for Generative AI, Architectural Tech Debt Costs, Harvard's Intro to AI with Python, MLOps at Reasonable Scale, Securing AI Systems Series + more 🚀ml-security · mlops · ml-education #230May 2023The MLOps Fundamentals Guide, AI Prompt Injection Explained, Binance Real Time ML for Fraud, Scaling Prime Video Infrastructure, CMU Database Group Youtube + more 🚀mlops · ml-security #219Feb 2023NeurIPS 2022 Production ML Videos, MIT Intro to Data-Centric ML, ML Innovation at Spotify with Ray + more 🚀ml-security · mlops #217Feb 2023Awesome Production ML OSS, Tech Behind Github Code Search, Preparing for the Europe AI Act, Rise of Enterprise AI Leadership, React.js The Documentary + more 🚀ml-security · ai-policy #206Nov 2022PyData Global 2022 Coming Up, Algorithmic Responsibility Panel, Securing ML Algorithms in EU, Large Language Models Review, SICP Key CompSci Foundation + more 🚀llms · ml-security · ai-policy #204Nov 2022Metadata In End To End MLOps, NeurIPS on Prod ML Challenges, The Modern Startup Architecture, TikTok SotA Recommender Sys, The Stream Processing Index + more 🚀mlops · ml-security · recommender-systems #195Sept 2022Best Practices for ML Engineering, NCSC Principles for ML Security, Practical OCR with PaddleOCR, Large Scale RecSys at Alibaba, PapersWithCode Annual Trends + more 🚀mlops · ml-security · recommender-systems #194Sept 2022Secure Machine Learning Talk, Stable Diffusion Public Release, Popular NLP Projects 2022, CompSci Papers We Love, Code Performance Speed Limits + more 🚀ml-security · generative-ai · nlp #190Aug 2022FastAI Practical ML Course, Golang Based ML Framework, JuliaCon Recordings Released, MLSecOps Top 10 Vulnerabilities, Building Containers From Scratch + more 🚀ml-education · mlops · ml-security #189Jul 2022MLSecOps Top 10 Vulnerabilities, Uber's Data Workflows at Scale, Implementing Research Papers, DeepMind AlphaFold Universe, Statistical ML Summer School + more 🚀ml-security · mlops · ml-research #179May 2022PyCon Machine Learning Security, Approaching (Almost) all ML Book, Airbnb's Microservice Architecture, Image Outlier Detection Tutorial, The HackerNews Algo Internals + more 🚀ml-security · forecasting #172Apr 2022Secure ML with MLSecOps, The State of Data Engineering, Doordash Declarative Fabricator, Google Brain Distributed Flow ML, Hashicorp from CEO to Tech IC + more 🚀mlops · ml-security · data-engineering #169Mar 2022The Future of AI Infrastructure, Radar Trends to Watch March, Cloud Resources for DL Training, Google NLP Model for Everything, Cloud Security Themes for 2022 + more 🚀mlops · llms · ml-security #136Jul 2021A Time Series DB from Scratch, Best of Speed & Simpl. w Julia, Towards Next Gen Dataflow, The Future of Deep Learning, Privacy & Cybersecurity Merging + more 🚀ml-security #135Jul 2021Drift Detection: An Introduction, The HashiCorp OpenCore Story, Guide to Onboarding Developers, Neural Net in Julia from Scratch, Exploiting Security in ML Binaries + more 🚀mlops · ml-security · gpu-compute #122Apr 2021Exploiting Security ML Pickles, Free AutoML Online Course, Neural Networks in Minecraft, ML Deployment Online Course, Defining DataOps and MLOps + more 🚀ml-security · mlops · ml-research #114Feb 2021Gen Z and Artificial Intelligence, Security in Prod ML Systems, How To Do All in Computer Vision, Medicine's ML Problem, Top 50 Matplotlib Visualisations + more 🚀ml-security · ai-ethics · computer-vision #81Jul 2020Getting ML into Production, Top Books on ML Feature Eng, MSFT Adversarial ML in Industry, Google on Neural Nets for Tables, Getting into a Causal Flow + more 🚀ml-security · nlp · ml-research #65Mar 2020Explainability, Security & MLOps, Python Machine Learning Books, DevOps in Machine Learning, A Tour on E2E ML Platforms, Adversarial ML Reading List + more 🚀mlops · explainability · ml-security #64Mar 2020Kubernetes ML for Everyone, Production-Ready ML Systems, Explaining Long Term ML Impact, Quantifying Reproducibility of ML, Adversarial Examples Resource + more 🚀mlops · ai-ethics · ml-security #51Dec 2019Play Endless Game Built by AI, Gentle Intro to Model Selection, Code Reviews for Jupyter NBs, Netflix Releases Metaflow, Adversarial Detection Hands On + more 🚀mlops · ml-security · generative-ai #40Sept 2019Tricking ML Classifiers, ML deployment paradigm, Five must-know graph algorithms, Survey fairness and bias in ML, Google's OSS differential privacy + more 🚀ml-security · mlops · ai-ethics #38Sept 2019Continuous Delivery for ML, AIOps and why you should care, Lang models as knowledge bases, AWS data security best practices, A smooth approach to prod ML + more 🚀mlops · ml-security #34Aug 2019A survey on the state of AutoML, Got speech? Voice Applications, Cloud native semantic text search, Learning from adversaries, Python-compatible spreadsheets + more 🚀ml-research · ml-security #31Jul 2019End-to-end XAI in production, Causal inference to improve UX, Managing ML in enterprise, Intro to Adversarial Examples, The GAN Story so far + more 🚀explainability · ml-research · ml-security #30Jul 2019Production-level ML Explainers, AI Explanations w Counterfactuals, Privacy & Cybersecurity Merging, Hightlights of AI O'Reilly Beijing, 18 Impressive GANs Applications + more 🚀explainability · ml-security · generative-ai #29Jul 2019Major trends in AI & Data, Production-level AI Explanations, 85% of Big Data Projects Fail, ML Mastery on building GANs, Question-answering AI in K8s + more 🚀explainability · data-engineering · ml-security #28Jul 2019The state of AI in 2019, Production ML in 2019, Model governance and ops, The best of modern NLP, Adversarial examples with FGSM + more 🚀mlops · explainability · ml-security #5Jan 2019XAI - eXplainability library for AI, Deep neural inspection, AI against alzheimer's disease, Differential privacy for tensorflow, The role of ML in databases + more 🚀explainability · ml-security #2Dec 2018Towards pandas 1.0, Top 50 matplotlib visualisations, Papers with code, An introduction to kubeflow, Style-based Face Generators, Adversarial debugging for NLP + more 🚀generative-ai · ml-security