Here's your daily roundup of the most relevant AI and ML news for April 01, 2026. Today's digest includes 1 security-focused story. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. Axios Supply Chain Attack Pushes Cross-Platform RAT via Compromised npm Account
The popular HTTP client known as Axios has suffered a supply chain attack after two newly published versions of the npm package introduced a malicious dependency that delivers a trojan capable of targeting Windows, macOS, and Linux systems. Versions 1.14.1 and 0.30.4 of Axios have been found to i...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
2. Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
arXiv:2603.29038v1 Announce Type: cross Abstract: Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an adversarial fine-tuning method that bypasses Anthropic's Constituti...
Source: arXiv - AI | 10 hours ago
3. Adversarial Prompt Injection Attack on Multimodal Large Language Models
arXiv:2603.29418v1 Announce Type: cross Abstract: Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly rely ...
Source: arXiv - AI | 10 hours ago
4. AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models
arXiv:2603.29410v1 Announce Type: cross Abstract: Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal alignment, ...
Source: arXiv - AI | 10 hours ago
5. CivicShield: A Cross-Domain Defense-in-Depth Framework for Securing Government-Facing AI Chatbots Against Multi-Turn Adversarial Attacks
arXiv:2603.29062v1 Announce Type: cross Abstract: LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current defenses, and single-layer guardrails are bypassed with similar rates. We present CivicShield, a cross-...
Source: arXiv - AI | 10 hours ago
6. Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers
arXiv:2603.28013v1 Announce Type: cross Abstract: We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate (ASR); we localize the pipeline stage at which each model's defense activates. We instrument e...
Source: arXiv - Machine Learning | 10 hours ago
7. FlowPure: Continuous Normalizing Flows for Adversarial Purification
arXiv:2505.13280v2 Announce Type: replace Abstract: Despite significant advances in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has emerg...
Source: arXiv - Machine Learning | 10 hours ago
8. Evasion Adversarial Attacks Remain Impractical Against ML-based Network Intrusion Detection Systems, Especially Dynamic Ones
arXiv:2306.05494v5 Announce Type: replace-cross Abstract: Machine Learning (ML) has become pervasive, and its deployment in Network Intrusion Detection Systems (NIDS) is inevitable due to its automated nature and high accuracy compared to traditional models in processing and classifying large vo...
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.