Here's your daily roundup of the most relevant AI and ML news for October 17, 2026. We're also covering 7 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. 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
3. 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
4. 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
5. A Multi-Tiered AI Accessibility Model (MAIAM): Proportionate Access and Capability Limits for Comprehensive Frontier AI Safety
arXiv:2610.20921v1 Announce Type: new Abstract: Most debate about releasing capable AI systems treats the choice as binary: keep the model behind an API, or publish the weights. That framing runs together two separate decisions. One is how capable a system may become. The other is who may obtain...
Source: arXiv - AI | 10 hours ago
6. Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation
arXiv:2610.21135v1 Announce Type: cross Abstract: LLM-agent evaluation reports behavioral scores but leaves the identity of the deployed runtime stack unreported. A tampered deployment that preserves evaluated outputs passes every output-only evaluator. We introduce DIB-Bench, a benchmark that m...
Source: arXiv - AI | 10 hours ago
7. Decoding What iOS Location Services Send to Apple: An LLM Is an Unreliable Analyst but a Useful Toolmaker
arXiv:2610.21597v1 Announce Type: cross Abstract: Reverse engineering the data formats used by mobile software is skilled and slow, and using AI to assist with it is attractive. We evaluate this for the protobuf messages that an iPhone sends to Apple's location services. Working from Apple's bin...
Source: arXiv - AI | 10 hours ago
Tech & Development
8. Show HN: Which Mac runs which LLM, and how fast
Article URL: https://macyou.co/mac-llm-calculator Comments URL: https://news.ycombinator.com/item?id=50130442 Points: 11
Comments: 4
Source: Hacker News - AI | 1 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.