Stress-Testing the Future: Building Resilient Mobile Apps at Scale
Uber engineers detail how AI-powered fault injection is proactively identifying and resolving vulnerabilities in their massive mobile infrastructure.
Science
Taming the Instability of Giant AI Models
Researchers have identified a key mechanism driving training failures in large language models and developed an optimizer to address it.
Hidden Weaknesses in the Satellite Web
A new analysis reveals that Low Earth Orbit satellite networks harbor unexpected vulnerabilities that standard network metrics fail to detect.
Decoding Pipeline Failures with AI
This research explores how artificial intelligence can dramatically reduce the time and effort required to diagnose and resolve issues in modern software delivery pipelines.
Fragile Guardians: When Cybersecurity AI Fails and Why It’s Hard to Tell
![Feature sensitivity analysis, quantified through gradient-based methods [latex] (Eq.5) [/latex], reveals vulnerabilities in phishing website detection, and this susceptibility is further underscored by significant drift in mean SHAP attributions when subjected to adversarial perturbations [latex] (Eq.6) [/latex].](https://arxiv.org/html/2602.06395v1/figures/feature_vulnerability_2panel_hbar.png)
New research reveals that machine learning models protecting critical systems are surprisingly vulnerable to subtle attacks, and that improving their resilience can impact how easily we understand their decisions.
Can AI Truly Spot Software Flaws?
![The study demonstrates that state-of-the-art large language models exhibit varying performance in vulnerability detection and reasoning, as quantified by metrics including Precision [latex]RPR\_P[/latex], Recall [latex]RRR\_R[/latex], and [latex]F_1[/latex] score [latex]RF_1[/latex], and that performance is notably influenced by the prompting strategy employed-specifically, a comparison between basic prompting and the utilization of CWE-generalized prompts.](https://arxiv.org/html/2602.06687v1/x3.png)
New research explores how to make large language models more reliable at identifying vulnerabilities in code.
Beyond Black Boxes: Smarter Epidemic Forecasting with Hybrid Models
A new approach combines the strengths of neural networks and traditional epidemiological models to overcome the challenges of noisy, incomplete data and improve prediction accuracy.
Predicting Power Swings: A New Approach to Wind Forecasting
A novel forecasting framework leverages agentic systems and frequency-aware modeling to anticipate and reconstruct critical ramp events in wind power generation.
The UK AI Landscape: Where Code Meets Capital
New research reveals how geographical concentration and firm characteristics are shaping success in Britain’s rapidly evolving artificial intelligence economy.
Reading Between the Lines: AI Accurately Assesses PTSD Severity
New research reveals that artificial intelligence can reliably estimate the severity of post-traumatic stress disorder from patient-provided narratives.