Here's your daily roundup of the most relevant AI and ML news for January 27, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
arXiv:2601.16890v1 Announce Type: cross Abstract: Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting noise or altering semantics, yet no existing framework exploits th...
Source: arXiv - Machine Learning | 18 hours ago
2. The Art of Being Difficult: Combining Human and AI Strengths to Find Adversarial Instances for Heuristics
arXiv:2601.16849v1 Announce Type: new Abstract: We demonstrate the power of human-LLM collaboration in tackling open problems in theoretical computer science. Focusing on combinatorial optimization, we refine outputs from the FunSearch algorithm [Romera-Paredes et al., Nature 2023] to derive sta...
Source: arXiv - Machine Learning | 18 hours ago
3. Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
arXiv:2601.17549v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security analysis of the protocol specification exists. We present the first rigorous security analysis o...
Source: arXiv - AI | 18 hours ago
4. Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM Crowdsourcing
arXiv:2505.21184v4 Announce Type: replace-cross Abstract: To prevent the misuse of Large Language Models (LLMs) for malicious purposes, numerous efforts have been made to develop the safety alignment mechanisms of LLMs. However, as multiple LLMs become readily accessible through various Model-as...
Source: arXiv - AI | 18 hours ago
5. On the Effects of Adversarial Perturbations on Distribution Robustness
arXiv:2601.16464v1 Announce Type: new Abstract: Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has revealed a...
Source: arXiv - Machine Learning | 18 hours ago
6. SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal Models
arXiv:2601.16231v1 Announce Type: cross Abstract: Multimodal foundation models that integrate audio, vision, and language achieve strong performance on reasoning and generation tasks, yet their robustness to adversarial manipulation remains poorly understood. We study a realistic and underexplor...
Source: arXiv - Machine Learning | 18 hours ago
7. UACER: An Uncertainty-Adaptive Critic Ensemble Framework for Robust Adversarial Reinforcement Learning
arXiv:2512.10492v2 Announce Type: replace Abstract: Robust adversarial reinforcement learning has emerged as an effective paradigm for training agents to handle uncertain disturbance in real environments, with critical applications in sequential decision-making domains such as autonomous driving...
Source: arXiv - Machine Learning | 18 hours ago
8. Physical Prompt Injection Attacks on Large Vision-Language Models
arXiv:2601.17383v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) are increasingly deployed in real-world intelligent systems for perception and reasoning in open physical environments. While LVLMs are known to be vulnerable to prompt injection attacks, existing methods eith...
Source: arXiv - AI | 18 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.