Here's your daily roundup of the most relevant AI and ML news for May 25, 2026. Today's digest includes 2 security-focused stories. We're also covering 6 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. TrapDoor Supply Chain Attack Spreads Credential-Stealing Malware via npm, PyPI, and CratesIO
A new coordinated cross-ecosystem software supply chain attack campaign has targeted npm, PyPI, and Crates.io to distribute credential-stealing malware.
The campaign, codenamed TrapDoor, spans more than 34 malicious packages across over 384 versions. The earliest activity was recorded on May 22,...
Source: The Hacker News (Security) | 8 hours ago
2. Packagist Supply Chain Attack Infects 8 Packages Using GitHub-Hosted Linux Malware
A new "coordinated" supply chain attack campaign has impacted eight packages on Packagist including malicious code designed to run a Linux binary retrieved from a GitHub Releases URL.
"Although the affected packages were all Composer packages, the malicious code was not added to composer.json," ...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
3. ALIVE: Awakening LLM Reasoning via Adversarial Learning and Instructive Verbal Evaluation
arXiv:2602.05472v2 Announce Type: replace Abstract: The quest for expert-level reasoning in Large Language Models (LLMs) has been hampered by a persistent \textit{reward bottleneck}: traditional reinforcement learning (RL) relies on scalar rewards that are \textbf{costly} to scale, \textbf{britt...
Source: arXiv - AI | 10 hours ago
4. WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents
arXiv:2605.23220v1 Announce Type: new Abstract: Despite the growing use of world models as decision-making agents, their adversarial robustness remains underexplored due to the lack of dedicated automated evaluation methods. A key obstacle is that attack evaluation must be both accurate and effi...
Source: arXiv - Machine Learning | 10 hours ago
5. Self-supervised Adversarial Purification for Graph Neural Networks
arXiv:2605.23239v1 Announce Type: new Abstract: Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicting objectives within a singl...
Source: arXiv - Machine Learning | 10 hours ago
6. Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
arXiv:2605.23351v1 Announce Type: new Abstract: We study adversarial multi-armed bandits with and without delayed feedback under a safety-aware goal: achieving minimax-optimal worst-case regret while keeping nearly constant regret relative to a designated "safe" baseline policy. Existing approac...
Source: arXiv - Machine Learning | 10 hours ago
7. Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
arXiv:2605.23411v1 Announce Type: new Abstract: Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Existing class-wise targeted attacks remain impractical for stealthy exploitation in this setting: sin...
Source: arXiv - Machine Learning | 10 hours ago
8. Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
arXiv:2605.23065v1 Announce Type: cross Abstract: Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floyd-Steinberg error-diffusion dithering as a lightweight, model-agno...
Source: arXiv - Machine Learning | 10 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.