Here's your daily roundup of the most relevant AI and ML news for February 11, 2026. Today's digest includes 2 security-focused stories. We're also covering 6 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. Show HN: OpenHarness – A harness for open source projects built by AI agents
AI agents now write most of my code and I have assumed the role of PM. So we are launching an experiment to learn from future PMs on how ideas will be built. We are micro launching Open Harness.Open Harness is a platform where AI agents will build your open source project idea for free using the ...
Source: Hacker News - ML Security | 1 hours ago
2. Self-hosted, memory-augmented AI chat that works with any LLM
Article URL: https://github.com/PStryder/Cathedral Comments URL: https://news.ycombinator.com/item?id=46981917 Points: 1
Comments: 1
Source: Hacker News - ML Security | 1 hours ago
Research & Papers
3. Not-in-Perspective: Towards Shielding Google's Perspective API Against Adversarial Negation Attacks
arXiv:2602.09343v1 Announce Type: new Abstract: The rise of cyberbullying in social media platforms involving toxic comments has escalated the need for effective ways to monitor and moderate online interactions. Existing solutions of automated toxicity detection systems, are based on a machine o...
Source: arXiv - AI | 18 hours ago
4. Stop Testing Attacks, Start Diagnosing Defenses: The Four-Checkpoint Framework Reveals Where LLM Safety Breaks
arXiv:2602.09629v1 Announce Type: cross Abstract: Large Language Models (LLMs) deploy safety mechanisms to prevent harmful outputs, yet these defenses remain vulnerable to adversarial prompts. While existing research demonstrates that jailbreak attacks succeed, it does not explain \textit{where}...
Source: arXiv - AI | 18 hours ago
5. MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
arXiv:2602.09222v1 Announce Type: cross Abstract: Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf. While these agents offer powerful capabilities, their design ex...
Source: arXiv - AI | 18 hours ago
6. Online Learning in MDPs with Partially Adversarial Transitions and Losses
arXiv:2602.09474v1 Announce Type: new Abstract: We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode. This model captures environments that are stable except at a few vulnerable...
Source: arXiv - Machine Learning | 18 hours ago
7. Deep Learning Foundation Models from Classical Molecular Descriptors
arXiv:2506.15792v2 Announce Type: replace Abstract: Fast and accurate data-driven prediction of molecular properties is pivotal to scientific advancements across myriad chemical domains. Deep learning methods have recently garnered much attention, despite their inability to outperform classical ...
Source: arXiv - Machine Learning | 18 hours ago
8. AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
arXiv:2601.17261v3 Announce Type: replace Abstract: Zeroth-Order (ZO) optimization has emerged as a promising solution for fine-tuning LLMs under strict memory constraints, as it avoids the prohibitive memory cost of storing activations for backpropagation. However, existing ZO methods typically...
Source: arXiv - Machine Learning | 18 hours ago
About This Digest
This digest is automatically curated from leading AI and tech news sources, filtered for relevance to AI security and the ML ecosystem. Stories are scored and ranked based on their relevance to model security, supply chain safety, and the broader AI landscape.
Want to see how your favorite models score on security? Check our model dashboard for trust scores on the top 500 HuggingFace models.