Here's your daily roundup of the most relevant AI and ML news for October 16, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
arXiv:2610.20776v1 Announce Type: cross Abstract: LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and interaction with remote services. This growing autonomy expands their exposure to indirect prompt i...
Source: arXiv - AI | 10 hours ago
2. CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty
arXiv:2610.22292v1 Announce Type: new Abstract: Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still exhibit dishonest behaviour, such as outputting claims that contradict some knowledge or are not sup...
Source: arXiv - Machine Learning | 10 hours ago
3. Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning
arXiv:2610.21547v1 Announce Type: new Abstract: Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a model from scratch. In this report, prepared for the 4th Federated Machine Learning International ...
Source: arXiv - Machine Learning | 10 hours ago
4. MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents
arXiv:2606.20717v2 Announce Type: replace-cross Abstract: Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation; however, they inherently expand the attack surface, introducing novel vision-based vulnerabilities. Existin...
Source: arXiv - AI | 10 hours ago
5. Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming
arXiv:2610.20941v1 Announce Type: cross Abstract: We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors. An LLM attacker edits a transcript so that the agent causes a specified harm, such as leaking an API key or spawning an unmonitore...
Source: arXiv - AI | 10 hours ago
6. Stateful Testing for Deep Learning Compilers
arXiv:2610.22003v1 Announce Type: cross Abstract: Modern deep learning compilers compile models lazily and cache artifacts across invocations. Retained compiler state can make a later invocation incorrect even when it is correct in isolation. An analysis of 26 publicly reported issues in PyTorch...
Source: arXiv - Machine Learning | 10 hours ago
7. Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions
arXiv:2610.22138v1 Announce Type: new Abstract: LLM systems increasingly rely on groups of agents that discuss, critique, and check one another, assuming that peers will catch individual errors. We test this assumption against a minimal adversary. In a ten-agent factual discussion, one or three ...
Source: arXiv - AI | 10 hours ago
8. Market Incentives for AI Safety Investment
arXiv:2610.21607v1 Announce Type: new Abstract: Despite their practical significance, modern AI systems pose significant societal risks, including toxicity, malicious use, and misinformation. Their mitigation depends not only on technical feasibility but also on the incentives of firms that deve...
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.