Here's your daily roundup of the most relevant AI and ML news for May 01, 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. SAP-Related npm Packages Compromised in Credential-Stealing Supply Chain Attack
Cybersecurity researchers are sounding the alarm about a new supply chain attack campaign targeting SAP-related npm Packages with credential-stealing malware. According to reports from Aikido Security, Onapsis, OX Security, SafeDep, Socket, StepSecurity, and Google-owned Wiz, the campaign –&...
Source: The Hacker News (Security) | 1 day ago
2. PyTorch Lightning and Intercom-client Hit in Supply Chain Attacks to Steal Credentials
In yet another software supply chain attack, threat actors have managed to compromise the popular Python package Lightning to push two malicious versions to conduct credential theft. According to Aikido Security, OX Security, Socket, and StepSecurity, the two malicious versions are versions 2.6.2...
Source: The Hacker News (Security) | 21 hours ago
Research & Papers
3. Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
arXiv:2604.27019v1 Announce Type: new Abstract: Safety-aligned language models must refuse harmful requests without collapsing into broad over-refusal, but the training-time mechanisms behind this tradeoff remain unclear. Prior work characterizes refusal directions and jailbreak robustness, yet ...
Source: arXiv - Machine Learning | 10 hours ago
4. Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
arXiv:2604.28129v1 Announce Type: cross Abstract: Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature in the...
Source: arXiv - AI | 10 hours ago
5. Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation
arXiv:2604.27249v1 Announce Type: cross Abstract: When instructed to underperform on multiple-choice evaluations, do language models engage with question content or fall back on positional shortcuts? We map the boundary between these regimes using a six-condition adversarial instruction-specific...
Source: arXiv - AI | 10 hours ago
6. Low Rank Adaptation for Adversarial Perturbation
arXiv:2604.27487v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large Language Models (LLMs) by updating neural network layers using low-r...
Source: arXiv - Machine Learning | 10 hours ago
7. Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders
arXiv:2604.28176v1 Announce Type: cross Abstract: Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine...
Source: arXiv - Machine Learning | 10 hours ago
8. Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI
arXiv:2501.19143v2 Announce Type: replace Abstract: As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial attacks manifest in two primary forms: deductive illusion, where specific stimuli are crafted bas...
Source: arXiv - AI | 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.