Here's your daily roundup of the most relevant AI and ML news for October 12, 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. CyberXero Uses Claude Code in Campaign That Stole Over 628,000 Ukrainian Records
Cybersecurity researchers have disclosed details of a two-pronged artificial intelligence (AI)-augmented initial access campaign targeting WordPress sites, e-commerce platforms, and critical infrastructure entities in Ukraine.
The activity, which brings together commodity offensive tools like Co...
Source: The Hacker News (Security) | 6 hours ago
Research & Papers
2. Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper
arXiv:2610.11542v2 Announce Type: replace-cross Abstract: Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden acceptance condition, malformed outputs that trigger retries, and compliance deadlocks ...
Source: arXiv - AI | 10 hours ago
3. Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal
arXiv:2505.15738v3 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted external content. This makes them a prime target for prompt injection attacks, in which an advers...
Source: arXiv - AI | 10 hours ago
4. A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models
arXiv:2610.13663v1 Announce Type: new Abstract: Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usually manual. This paper addresses the automatic tuning of these components and proposes a framew...
Source: arXiv - AI | 10 hours ago
5. LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
arXiv:2506.09956v2 Announce Type: replace-cross Abstract: Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the practical significance of this attack vector, existing benchmarks rely on small sets of template-ba...
Source: arXiv - AI | 10 hours ago
6. Improving Certified Robustness via Adversarial Distillation
arXiv:2606.31653v2 Announce Type: replace-cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set. For neural networks, cer...
Source: arXiv - AI | 10 hours ago
7. What Makes Adversarial Examples Transfer Across Deepfake Detectors?
arXiv:2609.10002v2 Announce Type: replace-cross Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibi...
Source: arXiv - AI | 10 hours ago
8. Controlled-Minimax: Stabilizing Adversarial Optimization via Control Theory
arXiv:2610.12915v1 Announce Type: new Abstract: Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles or divergence. This paper investigates these instabilities through the lens of continuous-time dy...
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.