Here's your daily roundup of the most relevant AI and ML news for January 30, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack
arXiv:2601.20903v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively constructing adversarial contexts from scratch and incrementally refining prompts. However, existing meth...
Source: arXiv - AI | 18 hours ago
2. Untargeted Jailbreak Attack
arXiv:2510.02999v3 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses. However, restricting the objective as inducing fixed targets inher...
Source: arXiv - AI | 18 hours ago
3. Fair Graph Machine Learning under Adversarial Missingness Processes
arXiv:2311.01591v5 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved state-of-the-art results in many relevant tasks where decisions might disproportionately impact specific communities. However, existing work on fair GNNs often assumes that either sensitive attributes ...
Source: arXiv - Machine Learning | 18 hours ago
4. False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systems
arXiv:2507.06252v2 Announce Type: replace-cross Abstract: Cyber Threat Intelligence (CTI) has emerged as a vital complementary approach that operates in the early phases of the cyber threat lifecycle. CTI involves collecting, processing, and analyzing threat data to provide a more accurate and r...
Source: arXiv - Machine Learning | 18 hours ago
5. Guided Perturbation Sensitivity (GPS): Detecting Adversarial Text via Embedding Stability and Word Importance
arXiv:2508.11667v2 Announce Type: replace Abstract: Adversarial text attacks remain a persistent threat to transformer models, yet existing defenses are typically attack-specific or require costly model retraining, leaving a gap for attack-agnostic detection. We introduce Guided Perturbation Sen...
Source: arXiv - Machine Learning | 18 hours ago
6. Adversarial Vulnerability Transcends Computational Paradigms: Feature Engineering Provides No Defense Against Neural Adversarial Transfer
arXiv:2601.21323v1 Announce Type: new Abstract: Deep neural networks are vulnerable to adversarial examples--inputs with imperceptible perturbations causing misclassification. While adversarial transfer within neural networks is well-documented, whether classical ML pipelines using handcrafted f...
Source: arXiv - Machine Learning | 18 hours ago
7. On the Adversarial Robustness of Learning-based Conformal Novelty Detection
arXiv:2510.00463v2 Announce Type: replace-cross Abstract: This paper studies the adversarial robustness of conformal novelty detection. In particular, we focus on two powerful learning-based frameworks that come with finite-sample false discovery rate (FDR) control: one is AdaDetect (by Marandon...
Source: arXiv - Machine Learning | 18 hours ago
8. OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence
arXiv:2601.21083v1 Announce Type: new Abstract: As large language models improve, so do their offensive applications: frontier agents now generate working exploits for under $50 in compute (Heelan, 2026). Defensive incident response (IR) agents must keep pace, but existing benchmarks conflate ac...
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.