Here's your daily roundup of the most relevant AI and ML news for January 21, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
arXiv:2601.12460v1 Announce Type: cross Abstract: The demand of customized large language models (LLMs) has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with malici...
Source: arXiv - Machine Learning | 18 hours ago
2. Adversarial News and Lost Profits: Manipulating Headlines in LLM-Driven Algorithmic Trading
arXiv:2601.13082v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted in the financial domain. Their exceptional capabilities to analyse textual data make them well-suited for inferring the sentiment of finance-related news. Such feedback can be leveraged by alg...
Source: arXiv - Machine Learning | 18 hours ago
3. Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
arXiv:2601.01747v3 Announce Type: replace-cross Abstract: Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle p...
Source: arXiv - Machine Learning | 18 hours ago
4. CausAdv: A Causal-based Framework for Detecting Adversarial Examples
arXiv:2411.00839v3 Announce Type: replace Abstract: Deep learning has led to tremendous success in computer vision, largely due to Convolutional Neural Networks (CNNs). However, CNNs have been shown to be vulnerable to crafted adversarial perturbations. This vulnerability of adversarial examples...
Source: arXiv - Machine Learning | 18 hours ago
5. NeuroShield: A Neuro-Symbolic Framework for Adversarial Robustness
arXiv:2601.13162v1 Announce Type: new Abstract: Adversarial vulnerability and lack of interpretability are critical limitations of deep neural networks, especially in safety-sensitive settings such as autonomous driving. We introduce \DesignII, a neuro-symbolic framework that integrates symbolic...
Source: arXiv - Machine Learning | 18 hours ago
6. Adversarial Drift-Aware Predictive Transfer: Toward Durable Clinical AI
arXiv:2601.11860v1 Announce Type: cross Abstract: Clinical AI systems frequently suffer performance decay post-deployment due to temporal data shifts, such as evolving populations, diagnostic coding updates (e.g., ICD-9 to ICD-10), and systemic shocks like the COVID-19 pandemic. Addressing this ...
Source: arXiv - Machine Learning | 18 hours ago
7. Generative Adversarial Networks for Resource State Generation
arXiv:2601.13708v1 Announce Type: cross Abstract: We introduce a physics-informed Generative Adversarial Network framework that recasts quantum resource-state generation as an inverse-design task. By embedding task-specific utility functions into training, the model learns to generate valid two-...
Source: arXiv - Machine Learning | 18 hours ago
8. Sy-FAR: Symmetry-based Fair Adversarial Robustness
arXiv:2509.12939v2 Announce Type: replace Abstract: Security-critical machine-learning (ML) systems, such as face-recognition systems, are susceptible to adversarial examples, including real-world physically realizable attacks. Various means to boost ML's adversarial robustness have been propose...
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.