Here's your daily roundup of the most relevant AI and ML news for January 16, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Cross-Platform Evaluation of Large Language Model Safety in Pediatric Consultations: Evolution of Adversarial Robustness and the Scale Paradox
arXiv:2601.09721v1 Announce Type: cross Abstract: Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities from an...
Source: arXiv - AI | 18 hours ago
2. Adversarial Evasion Attacks on Computer Vision using SHAP Values
arXiv:2601.10587v1 Announce Type: cross Abstract: The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise the performance of deep learning models by reducing output confidence or inducing misclassificatio...
Source: arXiv - AI | 18 hours ago
3. GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm
arXiv:2501.14230v4 Announce Type: replace-cross Abstract: Deep neural networks are highly vulnerable to adversarial examples, which are inputs with small, carefully crafted perturbations that cause misclassification -- making adversarial attacks a critical tool for evaluating robustness. Existin...
Source: arXiv - Machine Learning | 18 hours ago
4. Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
arXiv:2601.10543v1 Announce Type: new Abstract: Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is often s...
Source: arXiv - AI | 18 hours ago
5. Diffusion-Driven Deceptive Patches: Adversarial Manipulation and Forensic Detection in Facial Identity Verification
arXiv:2601.09806v1 Announce Type: cross Abstract: This work presents an end-to-end pipeline for generating, refining, and evaluating adversarial patches to compromise facial biometric systems, with applications in forensic analysis and security testing. We utilize FGSM to generate adversarial no...
Source: arXiv - AI | 18 hours ago
6. ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
arXiv:2601.10173v1 Announce Type: cross Abstract: Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are highly vulnerable to indirect prompt injection attacks, where maliciou...
Source: arXiv - AI | 18 hours ago
7. Transformer-Based Cognitive Radio: Adaptive Modulation Strategies Using Transformer Models
arXiv:2601.10519v1 Announce Type: new Abstract: Cognitive Radio (CR) systems, which dynamically adapt to changing spectrum environments, could benefit significantly from advancements in machine learning technologies. These systems can be enhanced in terms of spectral efficiency, robustness, and ...
Source: arXiv - Machine Learning | 18 hours ago
8. Robust and Efficient Zeroth-Order LLM Fine-Tuning via Adaptive Bayesian Subspace Optimizer
arXiv:2601.01452v3 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) with zeroth-order (ZO) optimization reduces memory by approximating gradients through function evaluations. However, existing methods essentially perform updates in a one-dimensional space, and suffer fr...
Source: arXiv - Machine Learning | 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.