Here's your daily roundup of the most relevant AI and ML news for June 03, 2026. Today's digest includes 1 security-focused story. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. Miasma Supply Chain Attack Compromises Red Hat npm Packages with Credential-Stealing Worm
A new Mini Shai-Hulud supply chain attack campaign, codenamed Miasma, has compromised @redhat-cloud-services packages to steal credentials and secrets from developer machines and deliver a self-propagating worm.
"This is effectively a Mini Shai-Hulud campaign: it uses the same core tactics of in...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
2. MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety
arXiv:2606.02630v1 Announce Type: cross Abstract: Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke authority. We introduce MultiTurnPSB, a four-turn adversarial extension of PatientSafetyBench, and eva...
Source: arXiv - AI | 10 hours ago
3. Gate AI: LLM Security Benchmark Evaluation Methodology and Results
arXiv:2606.02959v1 Announce Type: new Abstract: Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points. We describe an evaluation harness that addresses...
Source: arXiv - Machine Learning | 10 hours ago
4. NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense
arXiv:2606.03486v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translation, encoding, adversarial suffixes, and multi-turn buildup. Existing defenses still struggle to h...
Source: arXiv - AI | 10 hours ago
5. "Important You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems
arXiv:2606.03090v1 Announce Type: cross Abstract: The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educators ca...
Source: arXiv - AI | 10 hours ago
6. Position: Adversarial ML for LLMs Is Not Making Any Progress
arXiv:2502.02260v2 Announce Type: replace Abstract: In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings. Yet, progress has been slow even for simple "toy" problems (e.g., robustness to small adversarial p...
Source: arXiv - Machine Learning | 10 hours ago
7. Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines
arXiv:2605.25645v2 Announce Type: replace-cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TP...
Source: arXiv - AI | 10 hours ago
8. Phantom Transfer: Data Poisoning can Survive Data-Level Defences
arXiv:2602.04899v2 Announce Type: replace-cross Abstract: We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal lea...
Source: arXiv - AI | 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.