Here's your daily roundup of the most relevant AI and ML news for September 18, 2026. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers
arXiv:2609.19722v1 Announce Type: cross Abstract: Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce analyst-facing verdicts. This paper shows that the same reasoning capability introduces a new attack surfa...
Source: arXiv - Machine Learning | 10 hours ago
2. Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
arXiv:2609.19789v1 Announce Type: new Abstract: Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unknown. We study the vulnerability of LLM trading stacks to black-box, input-o...
Source: arXiv - AI | 10 hours ago
3. QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
arXiv:2602.04620v3 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 | 10 hours ago
4. FreqCondNorm: Towards Cross-domain Predictive Maintenance through a Frequency-Conditioned Transformer Foundation Model
arXiv:2609.20535v1 Announce Type: new Abstract: Deep learning predictive maintenance models suffer from poor transferability across machines and operating conditions, especially when labelled data are scarce and signals span five orders of magnitude in sampling frequency (1 Hz to ~100 kHz). We p...
Source: arXiv - AI | 10 hours ago
5. Adversarial Water-Filling: Theory, Algorithms, and a Domain-Specific Wireless Foundation Model
arXiv:2605.26163v2 Announce Type: replace-cross Abstract: Competitive resource allocation problems over frequency and space can be formulated as minimax interaction between transmit power and worst-case interference. This formulation naturally arises in multi-operator low Earth orbit (LEO) satel...
Source: arXiv - Machine Learning | 10 hours ago
6. Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability
arXiv:2502.17003v2 Announce Type: replace Abstract: Transfer-based adversarial attacks rely on surrogate models to craft perturbations, yet often overfit the surrogate's decision boundary. To address this problem, we propose Inverse Knowledge Distillation (IKD), a simple and attack-agnostic mech...
Source: arXiv - Machine Learning | 10 hours ago
7. Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks
arXiv:2602.06577v2 Announce Type: replace Abstract: Complex-valued neural networks (CVNNs) are rising in popularity for all kinds of applications. To safely use CVNNs in practice, analyzing their robustness against outliers is crucial. One well known technique to understand the behavior of deep ...
Source: arXiv - Machine Learning | 10 hours ago
Industry News
8. Is the AI safety debate about safety or control?
Not everyone agrees with Amodei's call for globally coordinated action for AI safety.
Source: TechCrunch - AI | 17 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.