Here's your daily roundup of the most relevant AI and ML news for April 02, 2026. Today's digest includes 3 security-focused stories. We're also covering 4 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. BastionLLM: Continuous security checks for LLM endpoints
BastionLLM lets you register your LLM endpoint and continuously test it for prompt injection, jailbreaks, and system‑prompt leakage. It starts with a safe connectivity check, verifies you own the endpoint, then runs adversarial scans and shows reports.If you’ve built LLM APIs (e.g. RAG apps) and ...
Source: Hacker News - ML Security | 1 hours ago
2. Claude Code Source Leaked via npm Packaging Error, Anthropic Confirms
Anthropic on Tuesday confirmed that internal code for its popular artificial intelligence (AI) coding assistant, Claude Code, had been inadvertently released due to a human error. "No sensitive customer data or credentials were involved or exposed," an Anthropic spokesperson said in a statement s...
Source: The Hacker News (Security) | 1 day ago
3. Google Attributes Axios npm Supply Chain Attack to North Korean Group UNC1069
Google has formally attributed the supply chain compromise of the popular Axios npm package to a financially motivated North Korean threat activity cluster tracked as UNC1069. "We have attributed the attack to a suspected North Korean threat actor we track as UNC1069," John Hultquist, chief analy...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
4. Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Classical Machine Learning and Deep Learning Optimization Techniques with Neurofeedback
arXiv:2509.14078v3 Announce Type: replace Abstract: This study investigates the performance of classifiers across EEG frequency bands, evaluating efficient class prediction for the left and right hemispheres using various optimisers. Three neural network architectures a deep dense network, a sha...
Source: arXiv - Machine Learning | 10 hours ago
5. MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning
arXiv:2604.00800v1 Announce Type: new Abstract: Plant phenology modelling aims to predict the timing of seasonal phases, such as leaf-out or flowering, from meteorological time series. Reliable predictions are crucial for anticipating ecosystem responses to climate change. While phenology modell...
Source: arXiv - Machine Learning | 10 hours ago
6. Adversarial Moral Stress Testing of Large Language Models
arXiv:2604.01108v1 Announce Type: new Abstract: Evaluating the ethical robustness of large language models (LLMs) deployed in software systems remains challenging, particularly under sustained adversarial user interaction. Existing safety benchmarks typically rely on single-round evaluations and...
Source: arXiv - AI | 10 hours ago
7. Bypassing Prompt Injection Detectors through Evasive Injections
arXiv:2602.00750v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to prompt injection attacks, where injected secondary prompts force the model to deviate from the user's instruc...
Source: arXiv - AI | 10 hours ago
Tech & Development
8. Show HN: A Homeostatic Logic-Funnel to Prevent RLHF Overrides in LLM Personas
Article URL: https://zenodo.org/records/18731691 Comments URL: https://news.ycombinator.com/item?id=47614126 Points: 1
Comments: 1
Source: Hacker News - AI | just now
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.