Here's your daily roundup of the most relevant AI and ML news for February 23, 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: CanaryAI v0.2.5 – Security monitoring on Claude Code actions
I've been using Claude Code a lot recently and wanted visibility into security-relevant executions — the kind of thing you may not necessarily catch while the agent is running.CanaryAI is a macOS menu bar app that monitors Claude Code session logs and alerts on suspicious behaviour: reverse shell...
Source: Hacker News - ML Security | 16 hours ago
2. Anthropic Launches Claude Code Security for AI-Powered Vulnerability Scanning
Artificial intelligence (AI) company Anthropic has begun to roll out a new security feature for Claude Code that can scan a user's software codebase for vulnerabilities and suggest patches. The capability, called Claude Code Security, is currently available in a limited research preview to Enterp...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
3. Generating adversarial inputs for a graph neural network model of AC power flow
arXiv:2602.17975v1 Announce Type: new Abstract: This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations. We demonstrate this capability on an ins...
Source: arXiv - Machine Learning | 1 hours ago
4. FENCE: A Financial and Multimodal Jailbreak Detection Dataset
arXiv:2602.18154v1 Announce Type: cross Abstract: Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly vulnerable because they process both text and images, creating broader attack surfaces. However, avai...
Source: arXiv - AI | 1 hours ago
5. On the Adversarial Robustness of Discrete Image Tokenizers
arXiv:2602.18252v1 Announce Type: cross Abstract: Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP encoders, thei...
Source: arXiv - AI | 1 hours ago
6. Provable Adversarial Robustness in In-Context Learning
arXiv:2602.17743v1 Announce Type: new Abstract: Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during pretraining. This...
Source: arXiv - Machine Learning | 1 hours ago
7. On the Adversarial Robustness of Learning-based Conformal Novelty Detection
arXiv:2510.00463v3 Announce Type: replace-cross Abstract: This paper studies the adversarial robustness of conformal novelty detection. In particular, we focus on two powerful learning-based frameworks that come with finite-sample false discovery rate (FDR) control: one is AdaDetect (by Marandon...
Source: arXiv - Machine Learning | 1 hours ago
8. Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
arXiv:2602.17835v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods such as TracIn and Influence Functions leverage influence to identify useful sample...
Source: arXiv - Machine Learning | 1 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.