Here's your daily roundup of the most relevant AI and ML news for March 12, 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: PromptSonar – Static analysis for LLM prompt security
I built PromptSonar because I kept seeing LLM security discussions focus entirely on runtime interception — but nobody was scanning the prompt strings written directly into source code before they ship.PromptSonar is a static analyzer that scans your codebase for prompt injection, jailbreaks,...
Source: Hacker News - ML Security | just now
2. Show HN: We analyzed 1,573 Claude Code sessions to see how AI agents work
We built rudel.ai after realizing we had no visibility into our own Claude Code sessions. We were using it daily but had no idea which sessions were efficient, why some got abandoned, or whether we were actually improving over time.So we built an analytics layer for it. After connecting our own s...
Source: Hacker News - ML Security | just now
Research & Papers
3. Solving adversarial examples requires solving exponential misalignment
arXiv:2603.03507v2 Announce Type: replace Abstract: Adversarial attacks - input perturbations imperceptible to humans that fool neural networks - remain both a persistent failure mode in machine learning, and a phenomenon with mysterious origins. To shed light, we define and analyze a network's ...
Source: arXiv - Machine Learning | 10 hours ago
4. Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks
arXiv:2603.10413v1 Announce Type: cross Abstract: Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim to mit...
Source: arXiv - AI | 10 hours ago
5. Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?
arXiv:2603.10689v1 Announce Type: new Abstract: Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the model. Such methods, although they remain empiricall...
Source: arXiv - Machine Learning | 10 hours ago
6. Evaluating randomized smoothing as a defense against adversarial attacks in trajectory prediction
arXiv:2603.10821v1 Announce Type: new Abstract: Accurate and robust trajectory prediction is essential for safe and efficient autonomous driving, yet recent work has shown that even state-of-the-art prediction models are highly vulnerable to inputs being mildly perturbed by adversarial attacks. ...
Source: arXiv - Machine Learning | 10 hours ago
7. Are Deep Speech Denoising Models Robust to Adversarial Noise?
arXiv:2503.11627v2 Announce Type: replace-cross Abstract: Deep noise suppression (DNS) models enjoy widespread use throughout a variety of high-stakes speech applications. However, we show that four recent DNS models can each be reduced to outputting unintelligible gibberish through the addition...
Source: arXiv - Machine Learning | 10 hours ago
8. Pretrained battery transformer (PBT): A foundation model for universal battery life prediction
arXiv:2512.16334v5 Announce Type: replace Abstract: Early prediction of battery cycle life is essential for improving battery design, manufacturing, and deployment. However, despite encouraging results with machine learning, progress remains constrained by scarce data and data heterogeneity acro...
Source: arXiv - Machine Learning | 10 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.