AIResearch

Security

Security at the intersection with AI: adversarial machine learning papers, red-teaming methodologies, defensive ML systems for cybersecurity, and the dual-use research questions that accompany increasingly capable models.

Security

Zscaler Embeds GPT-5.4-Cyber in Zero-Trust Detection Pipeline

Zscaler's TAC membership gives it early access to GPT-5.4-Cyber, embedding the security-tuned frontier model at the core of its detection pipeline and SDLC.

Apr 17 4 min read
Security

OpenAI Opens GPT-5.4-Cyber to Thousands of Verified Defenders

OpenAI releases GPT-5.4-Cyber with lower refusal boundaries and binary RE capabilities, scaling Trusted Access for Cyber from a limited pilot to thousands of verified security teams.

Apr 16 4 min read
Security

OpenAI Launches GPT-5.4-Cyber After Anthropic Restricts Mythos

GPT-5.4-Cyber gives defenders a restricted OpenAI model, but independent evaluation remains impossible as both companies compete on AI security framing.

Apr 14 4 min read
Network

AI Transforms Wireless Networks Through Open RAN

Machine learning is enabling smarter, more efficient cellular networks by tackling spectrum management, resource allocation, and security challenges in open radio access networks—paving the way for 6G.

Apr 3 4 min read
AI

AI Secures Wireless Networks Against Hidden Attacks

A new AI method dynamically switches between energy-saving and high-performance modes in smart surfaces, while defending against reward poisoning attacks that could cripple network reliability.

Apr 3 4 min read
AI

A Simpler Way to Measure Confidence in Safety Arguments

Researchers develop a new method to quantify confidence in safety assurance cases, helping engineers balance risk and cost without false precision.

Apr 2 4 min read
Science

AI Safety Gates Fail, But a Simple Check Succeeds

A new study shows that AI systems cannot reliably self-improve using traditional safety filters, but a verification method achieves perfect safety across scales, including large language models.

Apr 2 4 min read
Coding

Small AI Models Outperform Giants at Predicting Software Bugs

A new ensemble method using compact transformers can detect non-terminating programs more accurately than large language models, offering a practical solution for privacy-sensitive software analysis.

Apr 2 4 min read
AI

AI Models Learn Tasks, Not Users, for Better Privacy

A new federated learning method trains specialized AI models for specific tasks across distributed data, improving performance by up to 136% when handling multiple or unseen tasks without compromising privacy.

Apr 2 4 min read
AI

AI Spots Hidden Patterns in Customer Complaints

A new method uses AI to detect sudden drops in user sentiment across social media, helping companies identify real problems before they escalate.

Apr 2 4 min read
Data

Hidden Safety in AI Models Can Be Revived

Researchers discover that specialized AI models retain safety features but suppress them, and propose a lightweight fix to restore safety without losing performance.

Apr 2 3 min read
AI

AI Observers Could Make Self-Driving Cars Safer

A new AI layer detects hidden road hazards by understanding context, but a critical flaw in video processing reveals a safety gap that must be fixed before deployment.

Apr 2 4 min read
Data

AI Generates Fake Network Traffic to Improve Cybersecurity

A new AI method creates synthetic network data that helps intrusion detection systems spot both known and unknown attacks more accurately, boosting detection rates by up to 9.3% in tests.

Apr 2 3 min read
Security

Quantum Computers Could Crack Bitcoin Security Sooner Than Expected

New research reveals that quantum computers may break the cryptography securing billions in cryptocurrencies within years, forcing urgent upgrades to protect digital assets.

Apr 1 3 min read
Coding

New Tool Tests AI Agent Skills for Safety and Usefulness

SkillTester evaluates third-party AI skills by comparing them to baseline performance and running security probes, helping users avoid malicious or ineffective tools in growing agent ecosystems.

Apr 1 4 min read
Data

AI Safety Breakthrough for Small Language Models

A new defense method can detect and block malicious prompts in real-time without slowing down AI responses, making small language models safer for everyday use.

Apr 1 3 min read
Security

AI Backdoor Attacks Hide in Compressed Data

A new stealthy attack method can embed hidden triggers into condensed datasets, compromising AI models without detection while maintaining normal performance on clean tasks.

Apr 1 3 min read
Ethics

AI Safety Tests Miss How Models Amplify Human Harm

Researchers propose measuring 'harmful capability uplift'—how much AI increases users' ability to cause damage—arguing current safety evaluations fail to capture real-world risks where humans and AI collaborate on malicious tasks.

Apr 1 4 min read
Security

New AI Safety System Prevents Digital Assistants from Going Rogue

Researchers developed a framework that stops AI agents from executing harmful actions like deleting emails or leaking data, achieving over 95% accuracy in real-world tests.

Apr 1 4 min read
Data

AI Safety Gains a Database Theory Upgrade

A new equivalence shows that checking AI agent safety is exactly the same as evaluating a simple database query, unlocking decades of algorithmic results for faster and more reliable systems.

Apr 1 3 min read
Ethics

AI Could Make Online Dating Safer by Reading Nonverbal Cues

A new research agenda proposes using computer vision to detect discomfort and disinterest in video dates, aiming to close a communication gap that disproportionately harms women and vulnerable users.

Apr 1 4 min read
Security

AI Cybersecurity Tools Face Hidden Limits

A new mathematical theory reveals that AI cannot boost security operations past human bottlenecks, and common assumptions about false alarms are flawed.

Apr 1 4 min read
AI

New AI Method Protects Distributed Training from Attacks

A novel approach combines redundant computation and encoding to defend against malicious devices in distributed learning, reducing solution error and improving communication efficiency.

Apr 1 4 min read
Hardware

New Hardware Security Method Defeats AI Attacks

A simple resistor-capacitor device can protect Internet of Things gadgets from machine learning-based hacking attempts, offering a lightweight alternative to complex encryption.

Apr 1 4 min read