Here's your daily roundup of the most relevant AI and ML news for February 09, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
arXiv:2602.01539v2 Announce Type: replace-cross Abstract: Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, w...
Source: arXiv - Machine Learning | 18 hours ago
2. Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
arXiv:2507.02735v3 Announce Type: replace-cross Abstract: Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong effec...
Source: arXiv - AI | 18 hours ago
3. Explainable Transformer-Based Email Phishing Classification with Adversarial Robustness
arXiv:2511.12085v2 Announce Type: replace-cross Abstract: Phishing and related cyber threats are becoming more varied and technologically advanced. Among these, email-based phishing remains the most dominant and persistent threat. These attacks exploit human vulnerabilities to disseminate malwar...
Source: arXiv - Machine Learning | 18 hours ago
4. Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers
arXiv:2602.06395v1 Announce Type: cross Abstract: Machine learning (ML) models are increasingly deployed in cybersecurity applications such as phishing detection and network intrusion prevention. However, these models remain vulnerable to adversarial perturbations small, deliberate input modific...
Source: arXiv - Machine Learning | 18 hours ago
5. QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
arXiv:2602.04620v2 Announce Type: replace Abstract: GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approximations, however, they can lead to brittle optimization behavior, as global importance-ratio clipp...
Source: arXiv - Machine Learning | 18 hours ago
6. PurSAMERE: Reliable Adversarial Purification via Sharpness-Aware Minimization of Expected Reconstruction Error
arXiv:2602.06269v1 Announce Type: new Abstract: We propose a novel deterministic purification method to improve adversarial robustness by mapping a potentially adversarial sample toward a nearby sample that lies close to a mode of the data distribution, where classifiers are more reliable. We de...
Source: arXiv - Machine Learning | 18 hours ago
7. Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach
arXiv:2602.06404v1 Announce Type: new Abstract: We study distributed adversarial bandits, where $N$ agents cooperate to minimize the global average loss while observing only their own local losses. We show that the minimax regret for this problem is $\tilde{\Theta}(\sqrt{(\rho^{-1/2}+K/N)T})$, w...
Source: arXiv - Machine Learning | 18 hours ago
8. Refining the Information Bottleneck via Adversarial Information Separation
arXiv:2602.06549v1 Announce Type: new Abstract: Generalizing from limited data is particularly critical for models in domains such as material science, where task-relevant features in experimental datasets are often heavily confounded by measurement noise and experimental artifacts. Standard reg...
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.